http://mobinets.cn/site/api.php?action=feedcontributions&feedformat=atom&user=Zhiwei 2026-04-14T22:10:34Z User contributions MediaWiki 1.36.0 http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3511 2026-04-10T02:37:15Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2026-04-10 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = To effectively utilize heterogeneous specialized hardware units in modern GPUs, such as TensorCores and Tensor Memory Accelerators, this paper introduces PipeThreader, a new DNN compiler. PipeThreader proposes shifting scheduling functionality from hardware to software so as to enable more efficient and sophisticated computation pipelining with minimal manual effort. This is achieved through sTask-graph, a new DNN computation abstraction, a hierarchical hardware abstraction that captures the capabilities of specialized units, and new scheduling primitives. As a result, PipeThreader can discover efficient pipeline scheduling for well-studied DNN architectures like FlashAttention, achieving comparable or even superior performance. Additionally, it can uncover novel pipeline schemes for emerging models like Mamba2, delivering significantly better performance compared to state-of-the-art hand-crafted implementations. The code is open-sourced at https://github.com/tile-ai/tilelang.<br /> |confname =OSDI'25<br /> |link = https://www.usenix.org/conference/osdi25/presentation/cheng<br /> |title= PipeThreader: Software-defined pipelining for efficient DNN execution<br /> |speaker=Junzhe<br /> |date=2026-4-9<br /> }}<br /> <br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3508 2026-04-08T07:27:15Z

<p>Zhiwei: /* 报告顺序： */</p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2026）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://mns.uestc.cn/workshops/acst26 '''征文通知''']（如无法访问，可访问[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ 此链接]，需登录UESTC校内账号）<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序====<br /> '''Day 1: Apr. 16, 2026'''<br /> ----<br /> * '''''分组1：睡眠与作息'''''<br /> # 殷钰茹，自拟，智能手环使用对运动与睡眠质量的影响<br /> # 李孟晨，自拟，闹钟预设时间与实际起床时间间隔对剩余睡眠质量的影响<br /> # 李航通，自拟，高校课程时间分布对学生自主作息习惯的影响<br /> # 冉昊儒，自拟，宿舍熄灯制度对成员睡眠质量及日间精神状态的影响研究<br /> <br /> * '''''分组2：游戏竞技'''''<br /> # 邱之枫，自拟，王者荣耀发育路对线背后的经济增长研究<br /> # 冯子皓，自拟，CS2中急停操作熟练度对步枪远距离对枪命中率的影响研究<br /> # 刘泰宏，自拟，不完全信息、动态对抗、有限资源约束下，围绕位置、时间、信息、装备和目标进行的序贯博弈-CS2决策实证分析<br /> # 吴鸿飞，自拟，人格特质与决策思维的内在逻辑———以CS2职业选手性格画像与其战术行为、武器经济学的关联研究为例<br /> <br /> * '''''分组3：学习效率与课堂行为'''''<br /> # 范佳扬，自拟，高校课堂手机使用情况对听课效果的影响<br /> # 刘彦孜，自拟，基于系统活动记录的自习“假学习”识别工具<br /> # 李亦同，自拟，宿舍环境噪声对学习效率的干扰效应实验研究<br /> # 严浩文，自拟，监督成本差异下的旷课博弈策略<br /> <br /> * '''''分组4：认知心理与决策'''''<br /> # 项愉欣，自拟，呼吸连贯性对运动决策时间的影响<br /> # 李欣煜，自拟，基于发散联想任务（DAT）的AI与人类思维差异分析及测量工具改进<br /> # 卢一冉，自拟，考前焦虑对短期记忆提取与应试发挥的影响<br /> &lt;br&gt;<br /> '''Day 2: Apr. 23, 2026'''<br /> ----<br /> * '''''分组5：AI应用及系统'''''<br /> # 黄富祥，自拟，基于脑机接口的残疾人运动功能辅助系统设计与实现<br /> # 黄松，自拟，基于AI大语言模型的剧情自主推进式游戏<br /> # 伍红彬，MobiCom'25，HyperCam: Low-Power Onboard Computer Vision for IoT Cameras<br /> # 杨溢，NSDI'25，One-Size-Fits-None: Understanding and Enhancing Slow-Fault Tolerance in Modern Distributed Systems<br /> <br /> * '''''分组6：行为分析'''''<br /> # 杨思淇，自拟，小红书的素人种草信任机制分析<br /> # 况光奇，自拟，食堂饭菜对于周边餐饮发展的影响<br /> # 唐玺越，自拟，烹饪方式与核心温度对牛排熟度与口味的影响<br /> # 孙孟硕，自拟，“少冰”到底少了多少？——麦当劳可乐三种冰量配置的实证测量<br /> <br /> * '''''分组7：交通出行'''''<br /> # 闫旭，自拟，2号线东段改造、13号线和30号线开通等对龙泉驿居民出行习惯的影响<br /> # 白宇航，自拟，校园共享单车早晚供需失衡的时空分析<br /> # 李国兴，自拟，美伊战争背景下机票燃油附加费上调对异地情侣关系稳定性的影响<br /> <br /> * '''''分组8：文化与创意'''''<br /> # 刘成君，自拟，基于IPA的非语言发声音色克隆研究——以游戏角色《丝之歌》中的大黄蜂为例<br /> # 张胡泽，自拟，呼吸节奏对摄影快门时机与画面稳定性的影响<br /> # 张一哲，自拟，基于灰度映射的图片转字符画工具<br /> # 邓熠宸，自拟，以《龙族》和“追竞”为例对ai时代的同人创作和嗑糖文化的研究<br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期：<br /> ** 注册截止：2026.04.23<br /> ** 提交截止：2026.05.07<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3507 2026-04-08T07:26:50Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2026）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://mns.uestc.cn/workshops/acst26 '''征文通知''']（如无法访问，可访问[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ 此链接]，需登录UESTC校内账号）<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 16, 2026'''<br /> ----<br /> * '''''分组1：睡眠与作息'''''<br /> # 殷钰茹，自拟，智能手环使用对运动与睡眠质量的影响<br /> # 李孟晨，自拟，闹钟预设时间与实际起床时间间隔对剩余睡眠质量的影响<br /> # 李航通，自拟，高校课程时间分布对学生自主作息习惯的影响<br /> # 冉昊儒，自拟，宿舍熄灯制度对成员睡眠质量及日间精神状态的影响研究<br /> <br /> * '''''分组2：游戏竞技'''''<br /> # 邱之枫，自拟，王者荣耀发育路对线背后的经济增长研究<br /> # 冯子皓，自拟，CS2中急停操作熟练度对步枪远距离对枪命中率的影响研究<br /> # 刘泰宏，自拟，不完全信息、动态对抗、有限资源约束下，围绕位置、时间、信息、装备和目标进行的序贯博弈-CS2决策实证分析<br /> # 吴鸿飞，自拟，人格特质与决策思维的内在逻辑———以CS2职业选手性格画像与其战术行为、武器经济学的关联研究为例<br /> <br /> * '''''分组3：学习效率与课堂行为'''''<br /> # 范佳扬，自拟，高校课堂手机使用情况对听课效果的影响<br /> # 刘彦孜，自拟，基于系统活动记录的自习“假学习”识别工具<br /> # 李亦同，自拟，宿舍环境噪声对学习效率的干扰效应实验研究<br /> # 严浩文，自拟，监督成本差异下的旷课博弈策略<br /> <br /> * '''''分组4：认知心理与决策'''''<br /> # 项愉欣，自拟，呼吸连贯性对运动决策时间的影响<br /> # 李欣煜，自拟，基于发散联想任务（DAT）的AI与人类思维差异分析及测量工具改进<br /> # 卢一冉，自拟，考前焦虑对短期记忆提取与应试发挥的影响<br /> &lt;br&gt;<br /> '''Day 2: Apr. 23, 2026'''<br /> ----<br /> * '''''分组5：AI应用及系统'''''<br /> # 黄富祥，自拟，基于脑机接口的残疾人运动功能辅助系统设计与实现<br /> # 黄松，自拟，基于AI大语言模型的剧情自主推进式游戏<br /> # 伍红彬，MobiCom'25，HyperCam: Low-Power Onboard Computer Vision for IoT Cameras<br /> # 杨溢，NSDI'25，One-Size-Fits-None: Understanding and Enhancing Slow-Fault Tolerance in Modern Distributed Systems<br /> <br /> * '''''分组6：行为分析'''''<br /> # 杨思淇，自拟，小红书的素人种草信任机制分析<br /> # 况光奇，自拟，食堂饭菜对于周边餐饮发展的影响<br /> # 唐玺越，自拟，烹饪方式与核心温度对牛排熟度与口味的影响<br /> # 孙孟硕，自拟，“少冰”到底少了多少？——麦当劳可乐三种冰量配置的实证测量<br /> <br /> * '''''分组7：交通出行'''''<br /> # 闫旭，自拟，2号线东段改造、13号线和30号线开通等对龙泉驿居民出行习惯的影响<br /> # 白宇航，自拟，校园共享单车早晚供需失衡的时空分析<br /> # 李国兴，自拟，美伊战争背景下机票燃油附加费上调对异地情侣关系稳定性的影响<br /> <br /> * '''''分组8：文化与创意'''''<br /> # 刘成君，自拟，基于IPA的非语言发声音色克隆研究——以游戏角色《丝之歌》中的大黄蜂为例<br /> # 张胡泽，自拟，呼吸节奏对摄影快门时机与画面稳定性的影响<br /> # 张一哲，自拟，基于灰度映射的图片转字符画工具<br /> # 邓熠宸，自拟，以《龙族》和“追竞”为例对ai时代的同人创作和嗑糖文化的研究<br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期：<br /> ** 注册截止：2026.04.23<br /> ** 提交截止：2026.05.07<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3506 2026-04-08T07:00:20Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2026）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://mns.uestc.cn/workshops/acst26 '''征文通知''']（如无法访问，可访问[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ 此链接]，需登录UESTC校内账号）<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 16, 2026'''<br /> ----<br /> * '''''分组1：睡眠与作息'''''<br /> # 殷钰茹，自拟，智能手环使用对运动与睡眠质量的影响<br /> # 李孟晨，自拟，闹钟预设时间与实际起床时间间隔对剩余睡眠质量的影响<br /> # 李航通，自拟，高校课程时间分布对学生自主作息习惯的影响<br /> # 冉昊儒，自拟，宿舍熄灯制度对成员睡眠质量及日间精神状态的影响研究<br /> <br /> * '''''分组2：游戏竞技'''''<br /> # 邱之枫，自拟，王者荣耀发育路对线背后的经济增长研究<br /> # 冯子皓，自拟，CS2中急停操作熟练度对步枪远距离对枪命中率的影响研究<br /> # 刘泰宏，自拟，不完全信息、动态对抗、有限资源约束下，围绕位置、时间、信息、装备和目标进行的序贯博弈-CS2决策实证分析<br /> # 吴鸿飞，自拟，人格特质与决策思维的内在逻辑———以CS2职业选手性格画像与其战术行为、武器经济学的关联研究为例<br /> <br /> * '''''分组3：学习效率与课堂行为'''''<br /> # 范佳扬，自拟，高校课堂手机使用情况对听课效果的影响<br /> # 刘彦孜，自拟，基于系统活动记录的自习“假学习”识别工具<br /> # 李亦同，自拟，宿舍环境噪声对学习效率的干扰效应实验研究<br /> # 杨思淇，自拟，课间活动类型对课堂投入度的影响<br /> <br /> * '''''分组4：认知心理与决策'''''<br /> # 项愉欣，自拟，呼吸连贯性对运动决策时间的影响<br /> # 李欣煜，自拟，基于发散联想任务（DAT）的AI与人类思维差异分析及测量工具改进<br /> # 卢一冉，自拟，考前焦虑对短期记忆提取与应试发挥的影响<br /> &lt;br&gt;<br /> '''Day 2: Apr. 23, 2026'''<br /> ----<br /> * '''''分组5：AI应用及系统'''''<br /> # 黄富祥，自拟，基于脑机接口的残疾人运动功能辅助系统设计与实现<br /> # 黄松，自拟，基于AI大语言模型的剧情自主推进式游戏<br /> # 伍红彬，MobiCom'25，HyperCam: Low-Power Onboard Computer Vision for IoT Cameras<br /> # 杨溢，NSDI'25，One-Size-Fits-None: Understanding and Enhancing Slow-Fault Tolerance in Modern Distributed Systems<br /> <br /> * '''''分组6：行为分析'''''<br /> # 严浩文，自拟，监督成本差异下的旷课博弈策略<br /> # 况光奇，自拟，食堂饭菜对于周边餐饮发展的影响<br /> # 唐玺越，自拟，烹饪方式与核心温度对牛排熟度与口味的影响<br /> # 孙孟硕，自拟，“少冰”到底少了多少？——麦当劳可乐三种冰量配置的实证测量<br /> <br /> * '''''分组7：交通出行'''''<br /> # 闫旭，自拟，2号线东段改造、13号线和30号线开通等对龙泉驿居民出行习惯的影响<br /> # 白宇航，自拟，校园共享单车早晚供需失衡的时空分析<br /> # 李国兴，自拟，美伊战争背景下机票燃油附加费上调对异地情侣关系稳定性的影响<br /> <br /> * '''''分组8：文化与创意'''''<br /> # 刘成君，自拟，基于IPA的非语言发声音色克隆研究——以游戏角色《丝之歌》中的大黄蜂为例<br /> # 张胡泽，自拟，呼吸节奏对摄影快门时机与画面稳定性的影响<br /> # 张一哲，自拟，基于灰度映射的图片转字符画工具<br /> # 邓熠宸，自拟，以《龙族》和“追竞”为例对ai时代的同人创作和嗑糖文化的研究<br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期：<br /> ** 注册截止：2026.04.23<br /> ** 提交截止：2026.05.07<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Reading_List&diff=3505 2026-04-02T07:36:34Z

<p>Zhiwei: </p> <hr /> <div>== 2026 ==<br /> === Proceedings links ===<br /> * NSDI'26 Spring: https://www.usenix.org/conference/nsdi26/spring-accepted-papers<br /> * MobiCom'26: https://www.sigmobile.org/mobicom/2026/accepted.html<br /> * SigComm'26: https://conferences.sigcomm.org/sigcomm/2026/<br /> * INFOCOM'26: https://infocom2026.ieee-infocom.org/accepted-paper-list-main-conference<br /> * EuroSys'26: https://2026.eurosys.org/papers.html<br /> * MobiSys'26: https://www.sigmobile.org/mobisys/2026/program/<br /> <br /> === Interesting papers ===<br /> * [https://www.usenix.org/conference/nsdi26/presentation/lou HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public Clouds, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/xu FalconFS: Distributed File System for Large-Scale Deep Learning Pipeline, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/lu-jun Bridging Storage and Execution: A Semantic Virtual Bus for On-Demand Application Streaming, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/wu-bingyang FastServe: Iteration-Level Preemptive Scheduling for Large Language Model Inference, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/wu-tianyuan Attack of the Bubbles: Straggler-Resilient Pipeline Parallelism for Large Model Training, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/shen-yibin Law: Towards Consistent Low Latency in 802.11 Home Networks, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/liu-yuhan DroidSpeak: KV Cache Sharing Across Fine-tuned Model Variants, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/luo Agentix: An Efficient Serving Engine for LLM Agents as General Programs, NSDI'26]<br /> * [https://www.usenix.org/conference/nsdi26/presentation/hall Harvesting Spare CPU Resources in Container Systems, NSDI'26]<br /> <br /> == 2025 ==<br /> === Proceedings links ===<br /> * NSDI'25: https://www.usenix.org/conference/nsdi25/technical-sessions<br /> * MobiCom'25: https://www.sigmobile.org/mobicom/2025/program.html<br /> * INFOCOM'25: https://infocom2025.ieee-infocom.org/program/accepted-paper-list-main-conference<br /> * SigComm'25: https://conferences.sigcomm.org/sigcomm/2025/program/papers-info/<br /> * UbiComp'25: https://dl.acm.org/toc/imwut/2025/9/2<br /> * MobiSys'25: https://www.sigmobile.org/mobisys/2025/accepted_papers/ MobiSys'25<br /> <br /> === Interesting papers ===<br /> ==== MobiCom'25 ====<br /> * [https://arxiv.org/abs/2501.10547 HyperCam: Low-Power Onboard Computer Vision for IoT Cameras]<br /> * 5G-MAP: Demystifying the Performance Implications of Cloud-Based 5G Core Deployments<br /> * Towards Intelligent LiDAR with Adaptive Focus<br /> * B2LoRa: Boosting LoRa Transmission for Satellite-IoT Systems with Blind Coherent Combining<br /> * NeVo: Advancing Volumetric Video Streaming with Neural Content Representation<br /> * Wook: Enabling High-Throughput Wi-Fi Downlink with Ultra-Low Power<br /> * When Device Delays Meet Data Heterogeneity in Federated AIoT Applications<br /> * [https://arxiv.org/abs/2503.05346 AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications]<br /> ==== NSDI'25 ====<br /> * [https://www.usenix.org/conference/nsdi25/presentation/buckley Learnings from Deploying Network QoS Alignment to Application Priorities for Storage Services]<br /> * [https://www.usenix.org/conference/nsdi25/presentation/segarra GRANNY: Granular Management of Compute-Intensive Applications in the Cloud]<br /> * [https://www.usenix.org/conference/nsdi25/presentation/lu One-Size-Fits-None: Understanding and Enhancing Slow-Fault Tolerance in Modern Distributed Systems]<br /> * [https://www.usenix.org/conference/nsdi25/presentation/deng Minder: Faulty Machine Detection for Large-scale Distributed Model Training]<br /> <br /> == 2024 ==<br /> === Proceedings links ===<br /> * MobiCom 2023 (2024 in Oct.): https://sigmobile.org/mobicom/2023/accepted.html<br /> * INFOCOM 2024: https://infocom2024.ieee-infocom.org/program/accepted-paper-list-main-conference<br /> * NSDI 2024: https://www.usenix.org/conference/nsdi24/technical-sessions<br /> * SigComm 2024: https://conferences.sigcomm.org/sigcomm/2024/accepted-papers/<br /> * SenSys 2023 (2024 in Nov.): http://sensys.acm.org/2023/program/<br /> * MobiSys 2024: https://www.sigmobile.org/mobisys/2024/accepted-papers.html<br /> === Interesting papers ===<br /> * [MobiCom'24] [https://dl.acm.org/doi/pdf/10.1145/3636534.3649391 FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices]<br /> * [MobiCom'24] [https://dl.acm.org/doi/pdf/10.1145/3636534.3649363 Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices]<br /> * [ISCA'24] [https://arxiv.org/abs/2403.14353 DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/document/10621276 META-MCS: A Meta-knowledge Based Multiple Data Inference Framework]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/document/10621156 Few-Shot Data Completion for New Tasks in Sparse Crowdsensing]<br /> * [NSDI'22] [https://www.usenix.org/conference/nsdi22/presentation/zhang-anlan YuZu: Neural-Enhanced Volumetric Video Streaming]<br /> * [MobiCom'23] [https://dl.acm.org/doi/10.1145/3570361.3592525 FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform]<br /> * [MobiSys'24] [https://dl.acm.org/doi/10.1145/3643832.3661858 Theia: Gaze-driven and Perception-aware Volumetric Content Delivery for Mixed Reality Headsets]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/document/10621148 VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/document/10621116 Crucio: End-to-End Coordinated Spatio-Temporal Redundancy Elimination for Fast Video Analytics]<br /> * [MobiSys'24] [https://dl.acm.org/doi/10.1145/3643832.3661861 ChirpTransformer: Versatile LoRa Encoding for Low-power Wide-area IoT]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10621152 Edge-Assisted Camera Selection in Vehicular Networks]<br /> * [INFOCOM'23] [https://doi.org/10.1109/infocom53939.2023.10229101 Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing]<br /> * [ToN'24] [https://doi.org/10.1109/tnet.2023.3285093 Q-DDCA: Decentralized Dynamic Congestion Avoid Routing in Large-Scale Quantum Networks]<br /> * [TNSM'23] [https://doi.org/10.1109/tnsm.2023.3275815 Swapping-Based Entanglement Routing Design for Congestion Mitigation in Quantum Networks]<br /> * [SIGCOMM'24] [https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM: Adapting Large Language Models for Networking]<br /> * [NSDI'24] [https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> * [MobiSys'24] [https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> * [MobiSys'24] [https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> * [NSDI'24] [https://www.usenix.org/conference/nsdi24/presentation/alquraan LoLKV: The Logless, Linearizable, RDMA-based Key-Value Storage System]<br /> * [INFOCOM'24] [https://arxiv.org/abs/2404.02166 An Online Joint Optimization Approach for QoE Maximization in UAV-Enabled Mobile Edge Computing]<br /> * [MobiSys'24] [https://dl.acm.org/doi/abs/10.1145/3643832.3661856 LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices &amp; Networks]<br /> * [Mobicom'24] [https://dl.acm.org/doi/abs/10.1145/3636534.3649354 Venus: Enhancing QoE of Crowdsourced Live Video Streaming by Exploiting Multiflow Viewer Assistance]<br /> * [MobiCom'24] [https://dl.acm.org/doi/pdf/10.1145/3636534.3649359 Chorus: Coordinating Mobile Multipath Scheduling and Adaptive Video Streaming]<br /> * [SigComm'24] [https://dl.acm.org/doi/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> * [SigComm'24] [https://cs.stanford.edu/~keithw/sigcomm2024/sigcomm24-final380-acmpaginated.pdf Crux: GPU-Efficient Communication Scheduling for Deep Learning Training]<br /> * [SigComm'24] [https://cs.stanford.edu/~keithw/sigcomm2024/sigcomm24-final418-acmpaginated.pdf Eagle: Toward Scalable and Near-Optimal Network-WideSketch Deployment in Network Measurement]<br /> * [SigComm'24] [https://dl.acm.org/doi/10.1145/3651890.3672224 Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/abstract/document/10621116 Crucio: End-to-End Coordinated Spatio-Temporal Redundancy Elimination for Fast Video Analytics]<br /> * [INFOCOM'24] [https://ieeexplore.ieee.org/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> * [MobiSys'24] [https://dl.acm.org/doi/10.1145/3643832.3661861 ChirpTransformer: Versatile LoRa Encoding for Low-power Wide-area IoT]<br /> * [SigComm'24] [https://dl.acm.org/doi/abs/10.1145/3651890.3672213 In-Network Address Caching for Virtual Networks]<br /> <br /> == 2023 ==<br /> * [INFOCOM] https://infocom2023.ieee-infocom.org/program/accepted-paper-list-main-conference<br /> * [MobiCom] https://sigmobile.org/mobicom/2023/accepted.html<br /> * [SigComm] https://conferences.sigcomm.org/sigcomm/2023/list-accepted.html<br /> * [NSDI] https://www.usenix.org/conference/nsdi23/fall-accepted-papers<br /> * [SEC] http://acm-ieee-sec.org/2022/program.php<br /> * [MASS] https://cis.temple.edu/ieeemass2023/acceptedpapers.html<br /> <br /> == 2022 ==<br /> === INFOCOM 2022 ===<br /> Program site:https://infocom2022.ieee-infocom.org/program/accepted-paper-list-main-conference<br /> * [Edge] An Efficient Two-Layer Task Offloading Scheme for MEC Networks with Multiple Services Providers<br /> * [Edge] DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation<br /> * [Edge] Two Time-Scale Joint Service Caching and Task Offloading for UAV-assisted Mobile Edge Computing<br /> * [Edge] Towards Online Privacy-preserving Computation Offloading in Mobile Edge Computing<br /> * [Delivery] Joint Order Dispatch and Charging for Electric Self-Driving Taxi Systems<br /> * [Recharge] MDoC: Compromising WRSNs through Denial of Charge by Mobile Charger<br /> * [Recharge] Energy Saving in Heterogeneous Wireless Rechargeable Sensor Networks<br /> * [Network] Deadline-aware Multipath Transmission for Streaming Blocks<br /> * [IoT] FlexPatch: Fast and Accurate Object Detection for On-device High-Resolution Live Video Analytics<br /> * [Edge] DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation<br /> * [Edge] Optimizing Task Placement and Online Scheduling for Distributed GNN Training Acceleration<br /> * [Edge] Online File Caching in Latency-Sensitive Systems with Delayed Hits and Bypassing<br /> * [Edge] Distributed Cooperative Caching in Unreliable Edge Environments<br /> * [Edge] Enabling QoE Support for Interactive Applications over Mobile Edge with High User Mobility<br /> * [IoT] Encoding-based Range Detection in Commodity RFID Systems<br /> * [Edge] User Experience Oriented Task Computation for UAV-Assisted MEC System<br /> * [Edge] DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation<br /> * [Crowdsensing] Worker Selection Towards Data Completion for Online Sparse Crowdsensing<br /> * [Crowdsourcing] Learning for Crowdsourcing: Online Dispatch for Video Analytics with Guarantee<br /> * [IoT] PACC: Proactive and Accurate Congestion Feedback for RDMA Congestion Control<br /> * [Edge] Online Scheduling of Transmission and Processing for AoI Minimization with Edge Computing<br /> * [UAV] A Cloud-Terminal Collaborative System for Crowd Counting and Localization Using Multi-UAVs<br /> * [UAV] EFTA: An Energy-efficient, Fault-Tolerant, and Area-optimized UAV Placement Scheme for Search Operations<br /> * [Edge] EdgeMatrix: A Resources Redefined Edge-Cloud System for Prioritized Services<br /> * [IoT] IoTMosaic: Inferring User Activities from IoT Network Traffic in Smart Homes<br /> <br /> === Sigcomm 2022 ===<br /> Program site:http://conferences.sigcomm.org/sigcomm/2022/program.html<br /> * [IoT] Mobile access bandwidth in practice: measurement, analysis, and implications<br /> * [IoT] Understanding 5G Performance for Real-world Services: a Content Provider’s Perspective<br /> * [IoT] NeuroScaler: neural video enhancement at scale<br /> * [Cloud] From Luna to Solar: The Evolutions of the Compute-to-Storage Networks in Alibaba Cloud<br /> <br /> === ICNP 2022 ===<br /> Program site:https://icnp22.cs.ucr.edu/submission.html<br /> * [LoRa] X-MAC: Achieving High Scalability via Imperfect-Orthogonality Aware Scheduling in LPWAN<br /> * [LoRa] Is LoRaWAN Really Wide? Fine-grained LoRa Link-level Measurement in An Urban Environment<br /> <br /> === IPSN 2022 ===<br /> Program site:https://ipsn.acm.org/2022/program.html?v=1<br /> * [IoT] Furtively Connecting IoT Devices with Acoustic Noise<br /> * [IoT] Cappella: Establishing Multi-User Augmented Reality Sessions Using Inertial Estimates and Peer-to-Peer Ranging<br /> <br /> === NSDI 2022 ===<br /> Program site:https://www.usenix.org/conference/nsdi22/technical-sessions<br /> * [IoT] Exploiting Digital Micro-Mirror Devices for Ambient Light Communication<br /> * [LoRa] Sense Me on the Ride: Accurate Mobile Sensing over a LoRa Backscatter Channel<br /> * [LoRa] Saiyan: Design and Implementation of a Low-power Demodulator for LoRa Backscatter Systems<br /> * [IoT] Whisper: IoT in the TV White Space Spectrum<br /> * [Edge] Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers<br /> * [Delivery] Packet Order Matters! Improving Application Performance by Deliberately Delaying Packets<br /> <br /> === Mobisys 2022 ===<br /> Program site:https://www.sigmobile.org/mobisys/2022/accepted-papers.html<br /> * [IoT] Bringing WebAssembly to Resource-constrained IoT Devices for Seamless Device-Cloud Integration<br /> * [IoT] AutoCast: Scalable Infrastructure-less Cooperative Perception for Distributed Collaborative Driving<br /> * [Edge] Plantar Biometrics for Edge Computing<br /> <br /> === TMC 2022 ===<br /> * [IoT] Compressed Sensing Based Low-Power Multi-View Video Coding and Transmission in Wireless Multi-Path Multi-Hop Networks<br /> * [IoT] ECHO: Efficient Zero-Control-Packet Broadcasting for Mobile Ad Hoc Networks<br /> * [IoT] Sensory Data Aggregation in Internet of Things: Period-Driven Pipeline Scheduling Approach<br /> * [IoT] HearSmoking: Smoking Detection in Driving Environment via Acoustic Sensing on Smartphones<br /> * [IoT] Trine: Cloud-Edge-Device Cooperated Real-time Video Analysis for Household Applications<br /> * [IoT] WAVE: Edge-Device Cooperated Real-time Object Detection for Open-air Applications<br /> * [Edge] Online MEC Offloading for V2V Networks<br /> * [Edge] Reverse Auction-based Computation Offloading and Resource Allocation in Mobile Cloud-Edge Computing<br /> <br /> === TPDS 2022 ===<br /> * [Edge] Joint Coverage-Reliability for Budgeted Edge Application Deployment in Mobile Edge Computing Environment<br /> * [Network] Hydra: A Decentralized File System for Persistent Memory and RDMA Networks<br /> <br /> === IoTJ 2022 ===<br /> * [Crowdsensing] Nondeterministic Mobility based Incentive Mechanism for Efficient Data Collection in Crowdsensing<br /> * [Edge] Joint Shareability and Interference for Multiple Edge Application Deployment in Mobile-Edge Computing Environment<br /> <br /> == 2021 ==<br /> <br /> === Sensys 2021 ===<br /> Program site:http://sensys.acm.org/2021/program/<br /> * [Wireless] STeC: Exploiting Spatial and Temporal Correlation for Event-based Communication in WSNs<br /> * [Wireless] SpiderWeb: Enabling Through-Screen Visible Light Communication<br /> * [IoT] CurveLight: An Accurate and Practical Light Positioning System<br /> <br /> === INFOCOM 2021 ===<br /> Program site:https://infocom2021.ieee-infocom.org/accepted-paper-list-main-conference<br /> * [Wireless] WiForce: Wireless Sensing and Localization of Contact Forces on a Space Continuum<br /> * [LoRa] Radio Frequency Fingerprint Identification for LoRa Using Deep Learning<br /> * [LoRa] Pyramid: Real-Time LoRa Collision Decoding with Peak Tracking<br /> * [Edge] FedServing: A Federated Prediction Serving Framework Based on Incentive Mechanism<br /> * [UAV] Enhanced Flooding-Based Routing Protocol for Swarm UAV Networks: Random Network Coding Meets Clustering<br /> * [Edge] EdgeSharing: Edge Assisted Real-time Localization and Object Sharing in Urban Streets<br /> * [UAV] Towards Fine-Grained Spatio-Temporal Coverage for Vehicular Urban Sensing Systems<br /> * [UAV] Heuristic Algorithms for Co-scheduling of Edge Analytics and Routes for UAV Fleet Missions<br /> * [UAV] Minimizing the Number of Deployed UAVs for Delay-bounded Data Collection of IoT Devices<br /> * [Edge] Distributed Threshold-based Offloading for Large-Scale Mobile Cloud Computing<br /> * [Edge] Tailored Learning-Based Scheduling for Kubernetes-Oriented Edge-Cloud System<br /> * [Edge] Layer Aware Microservice Placement and Request Scheduling at the Edge<br /> * [Service Cache] Joint Cache Size Scaling and Replacement Adaptation for Small Content Providers<br /> * [Service Cache] Robust Service Mapping in Multi-Tenant Clouds<br /> * [Service Cache] Reliability-aware Dynamic Service Chain Scheduling in 5G Networks based on Reinforcement Learning<br /> * [Service Cache] GRADES: Gradient Descent for Similarity Caching<br /> <br /> === NSDI 2021 === <br /> Program site:https://www.usenix.org/conference/nsdi21/technical-sessions<br /> * [LoRa] Simplifying Backscatter Deployment: Full-Duplex LoRa Backscatter<br /> * [Wireless] WiForce: Wireless Sensing and Localization of Contact Forces on a Space Continuum<br /> * [Edge] Staying Alive: Connection Path Reselection at the Edge<br /> * [Edge] When to Hedge in Interactive Services<br /> * [Traffic Engineering] Cost-effective Cloud Edge Traffic Engineering with Cascara<br /> * [System] Ownership: A Distributed Futures System for Fine-Grained Tasks<br /> * [Service Chaining] Don't Yank My Chain: Auditable NF Service Chaining<br /> * [IoT] AIRCODE: Hidden Screen-Camera Communication on an Invisible and Inaudible Dual Channel<br /> * [Wireless] From Conception to Retirement: a Lifetime Story of a 3-Year-Old Wireless Beacon System in the Wild<br /> * [System] Programming Network Stack for Middleboxes with Rubik<br /> * [Routing] Staying Alive: Connection Path Reselection at the Edge<br /> * [System] EPaxos Revisited<br /> * [System] Elastic Resource Sharing for Distributed Deep Learning<br /> * [Sketch] Toward Nearly-Zero-Error Sketching via Compressive Sensing<br /> * [Coding] CodedBulk: Inter-Datacenter Bulk Transfers using Network Coding<br /> * [Network] ATP: In-network Aggregation for Multi-tenant Learning<br /> * [Distributed ML] Scaling Distributed Machine Learning with In-Network Aggregation<br /> * [Distributed Deep Learning] Elastic Resource Sharing for Distributed Deep Learning<br /> * [Wireless] One Protocol to Rule Them All: Wireless Network-on-Chip using Deep Reinforcement Learning<br /> <br /> === SIGCOMM 2021 ===<br /> Program site:https://conferences.sigcomm.org/sigcomm/2021/program.html<br /> <br /> * [Wireless] L2D2: low latency distributed downlink for LEO satellites<br /> * [Wireless] LAVA: Fine-grained 3D Indoor Wireless Coverage for Small IoT Devices<br /> * [SDN] Revisiting the Open vSwitch Ten Years Later<br /> * [Mechine Learning] Network Planning with Deep Reinforcement Learning <br /> * [LoRa] Concurrent Interference Cancellation: Decoding Multiple Packet Collisions in LoRa<br /> <br /> === MobiCom 2021 ===<br /> Program site:https://www.sigmobile.org/mobicom/2021/accepted.html<br /> <br /> * [Edge] Elf: Accelerate High-resolution Mobile Deep Vision with Content-aware Parallel Offloading<br /> * [IoT] Large-Scale Vehicle Trajectory Reconstruction with Camera Sensing Network<br /> * [IoT] HeadFi: Bringing Intelligence to All Headphones<br /> * [Wireless] A Community-Driven Approach to Democratize Access to Satellite Ground Stations<br /> <br /> === MobiSys 2021 ===<br /> Program site:https://www.sigmobile.org/mobisys/2021/program.html<br /> <br /> * [Wireless] Counting a stationary crowd using off-the-shelf wifi<br /> * [Wireless] Accurate Ubiquitous Localization with Off-the-Shelf IEEE 802.11ac Devices<br /> <br /> === IPSN 2021 ===<br /> Program site:https://ipsn.acm.org/2021/program.html?v=22<br /> <br /> * [LoRa] OwLL: Accurate LoRa Localization using the TV Whitespaces<br /> * [LoRa] A Novel Model-Based Security Scheme for LoRa Key Generation<br /> <br /> == 2020 ==<br /> <br /> === ICNP 2020 ===<br /> Program site:https://icnp20.cs.ucr.edu/program.html<br /> <br /> * [LoRa] AdapLoRa: Resource Adaptation for Maximizing Network Lifetime in LoRa Networks <br /> * [LoRa] CloakLoRa: A Covert Channel over LoRa PHY<br /> * [LoRa] Runtime Control of LoRa Spreading Factor for Campus Shuttle Monitoring<br /> * [LoRa] Long-Lived LoRa: Prolonging the Lifetime of a LoRa Network<br /> <br /> === IEEE Journals ===<br /> * [LoRa] [TII 2021] Extreme RSS Based Indoor Localization for LoRaWAN With Boundary Autocorrelation<br /> * [System] [TMC 2021] Predictability and Prediction of Human Mobility Based on Application-Collected Location Data<br /> * [Edge] [TMC 2021] Profit-Oriented Task Allocation for Mobile Crowdsensing With Worker Dynamics: Cooperative Offline Solution and Predictive Online Solution<br /> * [UAV] [TMC 2021] Multi-Area Throughput and Energy Optimization of UAV-Aided Cellular Networks Powered by Solar Panels and Grid<br /> * [UAV] [TMC 2021] Economic Analysis of Unmanned Aerial Vehicle (UAV) Provided Mobile Services<br /> * [Edge] [TMC 2021] Edge-Enabled V2X Service Placement for Intelligent Transportation Systems<br /> * [IoT] [TMC 2021] Real-Time Detection for Drowsy Driving via Acoustic Sensing on Smartphones<br /> * [Edge] [TWC 2021] D2D-Assisted Multi-User Cooperative Partial Offloading, Transmission Scheduling and Computation Allocating for MEC<br /> * [Edge] [IoTJ 2021] D2D-Enabled Mobile-Edge Computation Offloading for Multiuser IoT Network<br /> * [Edge] [TVT 2020] Latency Minimization for D2D-Enabled Partial Computation Offloading in Mobile Edge Computing<br /> * [Edge] [TWC 2019] Mobile-Traffic-Aware Offloading for Energy- and Spectral-Efficient Large-Scale D2D-Enabled Cellular Networks<br /> * [Edge] [TWC 2019] D2D Communications Meet Mobile Edge Computing for Enhanced Computation Capacity in Cellular Networks<br /> * [Edge] [JSAC 2017] On Consideration of Content Preference and Sharing Willingness in D2D Assisted Offloading<br /> * [Edge] [JSAC 2016] D2D Fogging: An Energy-efficient and Incentive-aware Task Offloading Framework via Network-assisted D2D Collaboration<br /> <br /> <br /> === INFOCOM 2020 ===<br /> Program site:https://infocom2020.ieee-infocom.org/accepted-paper-list-main-conference<br /> <br /> * [Edge] (How Much) Does a Private WAN Improve Cloud Performance?<br /> * [Wireless] A Zeroth-Order ADMM Algorithm for Stochastic Optimization over Distributed Processing Networks<br /> * [Edge] Towards Latency Optimization in Hybrid Service Function Chain Composition and Embedding<br /> * [Edge] A Fast Hybrid Data Sharing Framework for Hierarchical Mobile Edge Computing<br /> * [Charging Network] An Effective Multi-node Charging Scheme for Wireless Rechargeable Sensor Networks<br /> * [Edge] Camel: Smart, Adaptive Energy Optimization for Mobile Web Interactions<br /> * [Edge] Coded Edge Computing<br /> * [Edge] Collaborate or Separate? Distributed Service Caching in Mobile Edge Clouds<br /> * [LoRa] CoLoRa: Enable Muti-Packet Reception in LoRa<br /> * [Edge] Computation Scheduling for Wireless Powered Mobile Edge Computing Networks<br /> * [Edge] Cooperative Service Caching and Workload Scheduling in Mobile Edge Computing<br /> * [Edge] COSE: Configuring Serverless Functions using Statistical Learning<br /> * [Wireless] De-anonymization of Social Networks: the Power of Collectiveness<br /> * [Edge] Delay-Optimal Distributed Edge Computing in Wireless Edge Networks<br /> * [Edge] Distributed Collaborative 3D-Deployment of UAV Base Stations for On-Demand Coverage<br /> * [LoRa] DyLoRa: Towards Energy Efficient Dynamic LoRa Transmission Control<br /> * [Edge] Elastic Network Virtualization<br /> * [Wireless] Global Cooperation for Heterogeneous Networks<br /> * [Wireless] Hop-by-Hop Multipath Routing: Choosing the Right Nexthop Set<br /> * [Edge] HotDedup: Managing Hot Data Storage at Network Edge through Optimal Distributed Deduplication<br /> * [Wireless] How to Distribute Computation in Networks<br /> * [Path Plan] Informative Path Planning for Mobile Sensing with Reinforcement Learning<br /> * [5G Wireless] Is Deadline Oblivious Scheduling Efficient for controlling real-time traffic in cellular downlink systems?<br /> * [Edge] Joint Optimization of Signal Design and Resource Allocation in Wireless D2D Edge Computing<br /> * [Edge] Latency-aware VNF Chain Deployment with Efficient Resource Reuse at Network Edge<br /> * [LoRa] LiteNap: Downclocking LoRa Reception<br /> * [Edge] Network-Aware Optimization of Distributed Learning for Fog Computing<br /> * [Edge] Network Slicing in Heterogeneous Software-defined RANs<br /> * [Edge] Offloading Dependent Tasks in Mobile Edge Computing with Service Caching<br /> * [Code] On the Optimal Repair-Scaling Trade-off in Locally Repairable Codes<br /> * [Lora] Online Concurrent Transmissions at LoRa Gateway<br /> * [Edge] Online Placement of Virtual Machines with Prior Data<br /> * [IOT] OST: On-Demand TSCH Scheduling with Traffic-awareness<br /> * [Edge] PAM &amp; PAL: Policy-Aware Virtual Machine Migration and Placement in Dynamic Cloud Data Centers<br /> * [Charging Network] Placing Wireless Chargers with Limited Mobility<br /> * [Charging Network] An Effective Multi-node Charging Scheme for Wireless Rechargeable Sensor Networks<br /> * [Charging Network] Maximizing Charging Utility with Obstacles through Fresnel Diffraction Model<br /> * [Edge] Predictive Scheduling for Virtual Reality<br /> * [Edge] Reducing the Service Function Chain Backup Cost over the Edge and Cloud by a Self-adapting Scheme<br /> * [Localization] Selection of Sensors for Efficient Transmitter Localization<br /> * [Video Streaming] Streaming 360◦ Videos using Super-resolution<br /> * [Multi-Server Systems] Tiny Tasks - A Remedy for Synchronization Constraints in Multi-Server Systems<br /> * [Wireless] AZTEC: Anticipatory Capacity Allocation for Zero-Touch Network Slicing <br /> * [Wireless] OKpi: All-KPI Network Slicing Through Efficient Resource Allocation <br /> * [Crowd Sensing] Energy-Efficient UAV Crowdsensing with Multiple Charging Stations by Deep Learning<br /> * [UAV] VFC-Based Cooperative UAV Computation Task Offloading for Post-disaster Rescue<br /> * [UAV] ImgSensingNet: UAV Vision Guided Aerial-Ground Air Quality Sensing System<br /> * [Wireless] Dynamic Mobility-Aware Interference Avoidance for Aerial Base Stations in Cognitive Radio Networks<br /> * [Autonomous Driving] Sensing and Communication Integrated System for Autonomous Driving Vehicles<br /> * [Wireless] Enhancing Cellular Performance via Vehicular-based Opportunistic Relaying and Load Balancing<br /> * [Edge] Fog-based Data Offloading in Urban IoT Scenarios<br /> * [Edge] An Integrated Top-down and Bottom-up Task Allocation Approach in Social Sensing based Edge Computing Systems<br /> * [Wireless] Data-Intensive Routing in Delay Tolerant Networks<br /> * [Edge] A Scheduling Strategy for Reduced Power Consumption in Mobile Edge Computing<br /> * [AoI, Wireless] AoI and Throughput Tradeoffs in Routing-aware Multi-hop Wireless Networks<br /> * [AoI, Wireless] AoI Scheduling with Maximum Thresholds<br /> * [AoI, Wireless] Minimizing Age of Information in Multi-channel Time-sensitive Information Update Systems<br /> <br /> === MobiCom 2020===<br /> Program site:https://sigmobile.org/mobicom/2020/program.php<br /> <br /> * [Edge] EagleEye: Wearable Camera-based Person Identification in Crowded Urban Spaces<br /> * [RFID] Renovating Road Signs for Infrastructure-to-Vehicle Networking: A Visible Light Backscatter Communication and Networking Approach<br /> * [Localization] Voice Localization Using Nearby Wall Reflections<br /> * [Android] Experience: Aging or Glitching? Why Does Android Stop Responding and What Can We Do About It?<br /> * [Wireless] WiChronos : Energy-Efficient Modulation for Long-Range, Large-Scale Wireless Networks<br /> * [Video Streaming] NEMO: Enabling Neural-enhanced Video Streaming on Commodity Mobile Devices<br /> * [Federated Learning] Billion-Scale Federated Learning on Mobile Clients: A Submodel Design with Tunable Privacy<br /> * [Wireless] SociTrack: Infrastructure-Free Interaction Tracking through Mobile Sensor Networks<br /> * [LPWAN] Nephalai: Towards LPWAN C-RAN with Physical Layer Compression<br /> * [Edge] SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud<br /> * [Wireless] Microscope: Mobile Service Traffic Decomposition for Network Slicing as a Service<br /> * [Wireless] LMAC: Efficient Carrier-Sense Multiple Access for LoRa<br /> * [Wireless] Joltik: Enabling Energy-Efficient &quot;Future-Proof&quot; Analytics on Low-Power Wide-Area Networks<br /> * [Low-Power Network] Insect-scale Aerial Deployment of Wireless Sensors<br /> * [NB-IoT] Understanding Power Consumption of NB-IoT in the Wild: Tool and Large-scale Measurement<br /> * [AR] Ear-AR: Indoor Acoustic Augmented Reality on Earphones<br /> * [Wireless] Integrating Device, Cloud, and Client Development for IoT Applications with OneLink.<br /> * [Cloud] Integrating Device, Cloud, and Client Development for IoT Applications with OneLink.<br /> <br /> === SigComm 2020===<br /> Program site:https://conferences.sigcomm.org/sigcomm/2020/program.html<br /> <br /> * [Wireless] Concurrent entanglement routing for quantum networks: model and designs<br /> * [Wireless] Routing on Multiple Optimality Criteria<br /> * [Video Streaming] Server-driven video streaming for deep learning inference<br /> * [Video] Reducto: On camera filtering for resource-efficient real-time video analytics<br /> * [Edge] Fault-tolerant service function chaining<br /> * [Edge] Contention aware performance prediction for virtualized network functions<br /> * [Wireless] TACK: Improving wireless transport performance by taming acknowledgments<br /> * [Wireless, 5G] Beyond 5G reliable extreme mobility management<br /> * [Wireless, 5G] Understanding operational 5G: A first measurement study on its coverage, performance and energy consumption<br /> * [Wireless] Interpreting deep-learning based networking systems<br /> <br /> ===NSDI 2020===<br /> Program site:https://www.usenix.org/conference/nsdi20/accepted-papers<br /> <br /> * [Wireless] AccelTCP: Accelerating Network Applications with Stateful TCP Offloading<br /> * [Wireless] Contra: A Programmable System for Performance-aware Routing<br /> * [Wireless] Meaningful Availability<br /> * [Edge] Gandalf: An Intelligent, End-To-End Analytics Service for Safe Deployment in Large-Scale Cloud Infrastructure<br /> * [IOT] TinySDR: Low-Power SDR Platform for Over-the-Air Programmable IoT Testbeds<br /> * [Edge] Firecracker: Lightweight Virtualization for Serverless Applications<br /> * [Database] Millions of Tiny Databases<br /> * [Wireless] Rex: Preventing Bugs and Misconfiguration in Large Services Using Correlated Change Analysis<br /> * [Wireless] Check before You Change: Preventing Correlated Failures in Service Updates<br /> * [Wireless] Comb Decoding towards Collision-Free WiFi<br /> * [Wireless] AmphiLight: Direct Air-Water Communication with Laser Light<br /> * [Wireless] Comb Decoding towards Collision-Free WiFi<br /> * [Edge] Firecracker: Lightweight Virtualization for Serverless Applications<br /> * [Automobile] CarMap: Fast 3D Feature Map Updates for Automobiles<br /> <br /> ===IPSN 2020===<br /> Program site:https://ipsn.acm.org/2020/program.html<br /> <br /> * [IOT] Distributed Slot Scheduling for QoS Guarantee over TSCH-based IoT Networks via Adaptive Parameterization.<br /> * [Lora] SateLoc: A Virtual Fingerprinting Approach to Outdoor LoRa Localization using Satellite Images<br /> * [IOT] Robust Dynamic Hand Gesture Interaction using LTE Terminals<br /> * [Crowd Source] Road Grade Estimation Using Crowd-sourced Smartphone Data<br /> * [IOT] Understanding Deep Model Compression for IoT Devices<br /> * [Wireless] Low-Power Wide-Area Networks: Connect, Sense and Secure<br /> * [Edge] Activity Classification at the Edge<br /> * [LPWAN] Key Generation Scheme for LPWAN IoT Devices<br /> * [NFV] A Heterogeneous Parallel Packet Processing Architecture for NFV Acceleration<br /> * [Edge] Placement and Allocation of Virtual Network Functions: Multi-dimensional Case<br /> * [LPWAN] Quick (and Dirty) Aggregate Queries on Low-Power WANs<br /> <br /> == 2019 ==<br /> <br /> ===ICNP 2019===<br /> Program site:https://icnp20.cs.ucr.edu/program.html<br /> <br /> * [Wireless] Achieving Universal Low-Power Wide-Area Networks on Existing Wireless Devices<br /> * [Wireless] BeaconRider: Opportunistic Sharing of Beacon Air-Time in Densely Deployed WLANs<br /> * [Wireless] BDAC: A Behavior-aware Dynamic Adaptive Configuration on DHCP in Wireless LANs<br /> * [Wireless] Exploiting Rateless Codes and Cross-Layer Optimization for Low-Power Wide-Area Networks<br /> * [Lora] LoRaBee: Cross-Technology Communication from LoRa to ZigBee via Payload Encoding<br /> <br /> <br /> ===INFOCOM 2019===<br /> Program site:https://infocom2019.ieee-infocom.org/main-technical-program<br /> <br /> * [Edge] Joint Service Placement and Request Routing in Multi-cell Mobile Edge Computing Networks<br /> * [Wirelelss, IoT] CRF: Coexistent Routing and Flooding using WiFi Packets in Heterogeneous IoT Networks<br /> * [IoT, Charging] Charging Oriented Sensor Placement and Flexible Scheduling in Rechargeable WSN<br /> * [D2D] D2D Offloading for Statistical QoS Provisionings Over 5G Multimedia Mobile Wireless Networks<br /> * [Wireless] Interference Recycling: Exploiting Interfering Signals to Enhance Data Transmission<br /> * [Wireless] Enabling Cross-Technology Coexistence for Extremely Weak Wireless Devices<br /> * [IoT, Edge] Load Balancing for Interdependent IoT Microservices<br /> * [Networking, NF] Octans: Optimal Placement of Service Function Chains in Many-Core Systems<br /> * [Measurement, networking] Bound-based Network Tomography with Additive Metrics<br /> * [Link prediction, wireless] GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networks<br /> * [IoT, wireless] EE-IoT: An Energy-Efficient IoT Communication Scheme for WLANs<br /> * [Loc, wireless, IoT] iLPS: Local Positioning System with Simultaneous Localization and Wireless Communication<br /> * [NF, networking] Hierarchical Multi-resource Fair Queueing for Network Function Virtualization<br /> * [Measurement, SDN] Adaptive Path Tracing with Programmable Bloom Filters in Software-Defined Networks<br /> * [Edge] Service Placement with Provable Guarantees in Heterogeneous Edge Computing Systems<br /> * [Edge, NF] Joint Placement and Allocation of Virtual Network Functions with Budget and Capacity Constraints<br /> * [Mobile, system] Detecting Vulnerable Android Inter-App Communication in Dynamically Loaded Code<br /> * [IoT] Parameter Self-Configuration and Self-Adaptation in Industrial Wireless Sensor-Actuator Networks<br /> * [Measurement, caching] Counterintuitive Characteristics of Optimal Distributed LRU Caching Over Unreliable Channels<br /> * [Edge, crowdsensing] An Integrated Top-down and Bottom-up Task Allocation Approach in Social Sensing based Edge Computing Systems<br /> * [IoT, offloading] Fog-based Data Offloading in Urban IoT Scenarios<br /> * [Edge, DRL, QoE] Intelligent Edge-Assisted Crowdcast with Deep Reinforcement Learning for Personalized QoE<br /> * [IoT] Space-Optimal Packet Routing on Trees<br /> * [mmW] Smartlink: Exploiting Channel Clustering Effects for Reliable Millimeter Wave Communications<br /> * [UAV] PANDA: Placement of Unmanned Aerial Vehicles Achieving 3D Directional Coverage<br /> * [Video, DRL] DRL360: 360-degree Video Streaming with Deep Reinforcement Learning<br /> * [Edge] Hetero-Edge: Orchestration of Real-time Vision Applications on Heterogeneous Edge Clouds<br /> * [Edge] Service Placement and Request Scheduling for Data-intensive Applications in Edge Clouds<br /> * [App] UnseenCode: Invisible On-screen Barcode with Image-based Extraction <br /> * [VLC] SynLight: Synthetic Light Emission for Fast Transmission in COTS Device-enabled VLC <br /> * [IoT, lifetime] Maximum Lifetime Analytics in IoT Networks<br /> * [Federated learning] Federated Learning over Wireless Networks: Optimization Model Design and Analysis<br /> * [Federated learning] A Collaborative Learning Based Approach for Parameter Configuration of Cellular Networks<br /> * [Edge, offloading] Joint Offloading Decision and Resource Allocation with Uncertain Task Computing Requirement<br /> * [Edge] Winning at the Starting Line: Joint Network Selection and Service Placement for Mobile Edge Computing<br /> * [Edge] Adaptive User-managed Service Placement for Mobile Edge Computing: An Online Learning Approach<br /> * [charging, IoT] Minimizing Charging Delay for Directional Charging in Wireless Rechargeable Sensor Networks<br /> * [Wearable] WristSpy: Snooping Passcodes in Mobile Payment Using Wrist-worn Wearables<br /> * [App, mobile] NAuth: Secure Face-to-Face Device Authentication via Nonlinearity<br /> * [Blockchain] ACCEL: Accelerating the Bitcoin Blockchain for High-throughput, Low-latency Applications<br /> * [Networked learning] The Role of Network Topology for Distributed Machine Learning<br /> * [Edge] Adaptive Interference-Aware VNF Placement for Service-Customized 5G Network Slices<br /> * [Edge] Nomad: An Efficient Consensus Approach for Latency-Sensitive Edge-Cloud Applications<br /> * [Edge] A Distributed Orchestration Algorithm for Edge Computing Resources with Guarantees<br /> * [Charging Network] Collaborated Tasks-driven Mobile Charging and Scheduling A Near Optimal Result<br /> * [Charging Network] Minimizing Charging Delay for Directional Charging in Wireless Rechargeable Sensor Networks<br /> * [Charging Network] Charging Oriented Sensor Placement and Flexible Scheduling in Rechargeable WSNs<br /> <br /> <br /> ===MobiCom 2019===<br /> Program site: https://sigmobile.org/mobicom/2019/accepted.php<br /> <br /> * [App] Software Defined Cooking using a Microwave Oven<br /> * [LoRa] Challenge: Unlicensed LPWANs Are Not Yet the Path to Ubiquitous Connectivity<br /> * [Wearable] Experience: Design, Development and Evaluation of a Wearable Device for mHealth Applications<br /> * [App] HealthSense: Software-defined Mobile-based Clinical Trials<br /> * [Wireless] On-Off Noise Power Communication<br /> * [System] Living IoT: A Flying Wireless Platform on Live Insects<br /> * [Vehicle] VeMo: Enabling Transparent Vehicular Mobility Modeling at Individual Levels with Full Penetration<br /> * [App] SolarGest: Ubiquitous and Battery-free Gesture Recognition using Solar Cells<br /> * [Mobile] Fire in Your Hands: Understanding Thermal Behavior of Smartphones<br /> * [App] Taprint: Secure Text Input for Commodity Smart Wearables<br /> * [App] Keep Others From Peeking At Your Mobile Device Screen!<br /> * [Edge, AR] Edge Assisted Real-time Object Detection for Mobile Augmented Reality<br /> * [Measurement] An Active-Passive Measurement Study of TCP Performance over LTE on High-speed Rails<br /> * [Mobile] Optimizing Energy Efficiency of Browsers in Energy-Aware Scheduling–enabled Mobile Devices<br /> <br /> ===SigComm 2019===<br /> Program site: https://conferences.sigcomm.org/sigcomm/2019/program.html<br /> * [Networking] Gentle Flow Control: Avoiding Deadlock in Lossless Networks<br /> * [IoT, 5G] A Millimeter Wave Network for Billions of Things<br /> * [Mobile] E2E: Embracing User Heterogeneity to ImproveQuality of Experience on the Web<br /> * [Edge] Offloading Distributed Applications onto SmartNICs using iPipe<br /> * [Networking, QoE] End-to-End Transport for Video QOE Fairness<br /> * [VR, QoE] Pano: Optimizing 360 Video Streaming with a Better Understanding of Quality Perception<br /> * [Networking] On Optimal Neighbor Discovery<br /> <br /> ===NSDI 2019===<br /> Program site: https://www.usenix.org/conference/nsdi19/technical-sessions<br /> * [Networking] NetBouncer: Active Device and Link Failure Localization in Data Center Networks<br /> * [Networking, NF] Performance Contracts for Software Network Functions<br /> * [Networking, NF] Correctness and Performance for Stateful Chained Network Functions<br /> * [Blockchain] Monoxide: Scale out Blockchains with Asynchronous Consensus Zones<br /> * [Networking] Loom: Flexible and Efficient NIC Packet Scheduling<br /> * [Networking] Eiffel: Efficient and Flexible Software Packet Scheduling<br /> <br /> ===IPSN 2019===<br /> Program site: http://ipsn.acm.org/2019/program.html<br /> * [LoRa] LongShoT: Long-Range Synchronization of Time<br /> * [Edge, system] Event-triggered Natural Hazard Monitoring with Convolutional Neural Networks on the Edge<br /> * [VR] DeltaVR: Achieving High-Performance Mobile VR Dynamics through Pixel Reuse<br /> * [App] TennisEye: Tennis Ball Speed Estimation using a Racket-mounted Motion Sensor<br /> * [LoRa] Automated Estimation of Link Quality for LoRa: A Remote Sensing Approach.<br /> * [Wireless] ALICE: Autonomous Link-based Cell Scheduling for TSCH<br /> * [App] Can a phone hear the shape of a room?<br /> * [Wireless] Cross-Sender Bit-Mixing Coding<br /> <br /> ===MobiHoc 2019===<br /> Program site: https://www.sigmobile.org/mobihoc/2019/accepted-papers.html<br /> * [Robot, Nav] Robot Navigation in Radio Beam Space: Leveraging Robotic Intelligence for Seamless mmWave Network Coverage<br /> * [Measurement] How Bad is Selfish Caching?<br /> <br /> === ICDCS 2019 ===<br /> Program site: https://conferences.computer.org/icdcs/2019/#!/toc/0<br /> * [Networking] SpeedyBox: Low-Latency NFV Service Chains with Cross-NF Runtime Consolidation<br /> * [Dist. learning] Falcon: Towards Computation-Parallel Deep Learning in Heterogeneous Parameter Server196<br /> * [Streaming] Beyond QoE: Diversity Adaption in Video Streaming at the Edge<br /> * [Edge] DMRA: A Decentralized Resource Allocation Scheme for Multi-SP Mobile Edge Computing<br /> * [Edge] Incentivizing Microservices for Online Resource Sharing in Edge Clouds<br /> * [Edge] A Cyclic Game for Joint Cooperation and Competition of Edge Resource Allocation<br /> * [Charging] Near Optimal Charging Scheduling for 3-D Wireless Rechargeable Sensor Networks with Energy Constraints<br /> * [App] HyperEar: Indoor Remote Object Finding with a Single Phone678<br /> * [Edge, NFV] Providing Reliability-Aware Virtualized Network Function Services for Mobile Edge Computing <br /> * [IoT, measurement] Understanding Energy Efficiency in IoT App Executions<br /> * [IoT, Federated] DÏoT: A Federated Self-learning Anomaly Detection System for IoT<br /> * [App, acoustic] EchoWrite: An Acoustic-based Finger Input System Without Training<br /> * [IoT, AdHoc] Low-Latency Concurrent Broadcast Scheduling in Duty-Cycled Multihop Wireless Networks<br /> * [Charging] Minimizing the Longest Charge Delay of Multiple Mobile Chargers for Wireless Rechargeable Sensor Networks by Charging Multiple Sensors Simultaneously<br /> * [Edge, offload] Joint Online Edge Caching and Load Balancing for Mobile Data Offloading in 5G Networks<br /> * [DRL, VNF, Edge] Deep Reinforcement Learning Based VNF Management in Geo-distributed Edge Computing<br /> * [Blockchain, Edge] Hierarchical Edge-Cloud Computing for Mobile Blockchain Mining Game<br /> <br /> == 2018 ==<br /> <br /> === SenSys 2018 ===<br /> Program site: http://sensys.acm.org/2018/program/<br /> * [Loc] 3D Localization for Sub-Centimeter Sized Devices<br /> * [Loc] Accurate 3D Localization for 60 GHz Networks<br /> * [App, freetouch] UbiTap: Leveraging Acoustic Dispersion for Ubiquitous Touch Interface on Solid Surfaces<br /> * [AR] MARVEL: Enabling Mobile Augmented Reality with Low Energy and Low Latency<br /> * [VM for IoT] CapeVM: A Safe and Fast Virtual Machine for Resource-Constrained Internet-of-Things Devices<br /> * [IoT] Passive ZigBee: Enabling ZigBee Communication in IoT networks with 1000x Less Power Consumption<br /> <br /> === CoNext 2018 ===<br /> Program site: https://conferences2.sigcomm.org/co-next/2018/#!/program<br /> * [Measurement] Five Years at the Edge: Watching Internet from the ISP Network<br /> * [Sensing] Boosting fine-grained activity sensing by embracing wireless multipath effects<br /> * [Mobile, web] Proteus: Network-aware Web Browsing on Heterogeneous Mobile Systems<br /> <br /> === ICNP 2018 ===<br /> Program site: http://icnp18.cs.ucr.edu/program.html<br /> * [Edge] Dynamic Heterogeneity-Aware Coded Cooperative Computation at the Edge<br /> * [Edge, AR] DARE: Dynamic Adaptive Mobile Augmented Reality with Edge Computing<br /> * [NF] Virtual Network Function Deployment in Tree-structured Networks<br /> * [SDN, update] Hermes: Utility-aware Network Update in Software-defined WANs<br /> * [SDN, update, protocol] Shifter: A Consistent Multicast Routing Update Scheme in Software-Defined Networks<br /> * [Wireless, backscatter] Canon: Exploiting Channel Diversity for Reliable Parallel Decoding in Backscatter Communication</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3500 2026-03-05T08:01:09Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2026）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://mns.uestc.cn/workshops/acst26 '''征文通知''']（如无法访问，可访问[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ 此链接]，需登录UESTC校内账号）<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期2025.04.23 - 2025.04.30<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3499 2026-03-05T07:59:23Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2026）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://mns.uestc.cn/workshops/acst26 '''征文通知''']，如无法访问，可访问[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ 此链接]（需登录UESTC师生账号）<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期2025.04.23 - 2025.04.30<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3498 2026-03-05T04:21:24Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2026）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ '''征文通知''']<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期2025.04.23 - 2025.04.30<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3497 2026-03-05T04:04:56Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst26/ '''征文通知''']<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期2025.04.23 - 2025.04.30<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:AW&diff=3496 2026-03-05T01:23:29Z

<p>Zhiwei: </p> <hr /> <div>==专业写作基础课程==<br /> 总的来讲，这是一门介绍科研，科研入门，及学术<br /> 课程主要内容涉及学术创新、学术规范与论文写作。<br /> 其中学术创新部分，重点针对本科生群体介绍何谓创新、科研工作的特点、读研相关内容、学术论文的写作技巧与规范。<br /> [[File:aw_cover.png|thumb]]<br /> 课程目录如下：<br /> # 认识学术及科研入门<br /> #*学术研究概述及一般过程<br /> #*学术规范的意义<br /> #*研究者与非研究者<br /> #*读不读研？<br /> #*如何选择导师？<br /> #*如何选择研究领域？<br /> #*如何收集相关材料并阅读？<br /> #*如何进行科研选题？<br /> #科技论文谋划、构成与表达技巧<br /> #*如何谋划和开始一篇科技论文？<br /> #*科技论文构成与规范表达？<br /> #*科技论文插图与表格规范设计？<br /> #*科技论文式子的规范？<br /> #*如何写毕业设计论文？<br /> #学术规范指南<br /> #*如何进行学术署名？<br /> #*什么叫编、著与编著？<br /> #*科技论文引文规范是什么？<br /> #*科技论文语言规范<br /> <br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [[Resource:AW征文通知|'''征文通知''']]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> <br /> &lt;!--<br /> ==课程要求（2025）==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===课程论文===<br /> <br /> ====相关资料====<br /> * 课程PPT将会在课程群中发送<br /> * [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/workshops/acst25/ 征文通知]<br /> <br /> ====往届题目参考====<br /> * 基于哈希学习的快速法律条文推荐模型<br /> * 异类传感器的分布式检测和数据融合<br /> * 王者荣耀中的分层强化学习<br /> * 探究粉丝言论对消费者行为的影响——以《哪吒》为例<br /> * 加沙医院的预约系统改进方案<br /> * 关于防丢贴纸的改进与大规模商用的研究<br /> * 基于深度学习的微小曲面文本检测与识别<br /> * 电子科大低成本快递配送方案<br /> * 基于MATLAB的地形扫描车信息显示系统<br /> <br /> ===口头报告===<br /> ====要求及说明====<br /> * 每位同学汇报&lt;5分钟，讲清楚问题和挑战为主，严格控制时间（参考[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex0_fast_reading.pdf 案例1：快读]和[https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/course/AcademicWriting/examples/ex1_recaptcha.pdf 案例2：Recaptcha]）<br /> * 问答环节&lt;1个问题<br /> * 说明：<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> * 选择论文参考列表：[[Resource:Reading_List]]<br /> <br /> ====报告顺序：====<br /> '''Day 1: Apr. 10, 2025.'''<br /> ----<br /> * '''''Session 1: Mobile Computing'''''<br /> # 付文亮，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661894 ARISE: High-Capacity AR Offloading Inference Serving via Proactive Scheduling]<br /> # 林鑫，MobiSys 2024，[https://dl.acm.org/doi/abs/10.1145/3643832.3661855 Face Recognition In Harsh Conditions: An Acoustic Based Approach]<br /> # 王鹤潭，MobiCom 2023，[https://dl.acm.org/doi/abs/10.1145/3570361.3592532 Towards Flying Without Seeing For Autonomous Drones]<br /> # 杨益，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621152/ Edge-Assisted Camera Selection in Vehicular Networks]<br /> <br /> * '''''Session 2: Network systems'''''<br /> # 郭卓帆，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621134/ AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks]<br /> # 郑棹恒，NSDI 2024，[https://www.usenix.org/conference/nsdi24/presentation/hu Characterization of Large Language Model Development in the Datacenter]<br /> # 徐甄焱，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672268 NetLLM：Adapting Large Language Models for Networking]<br /> # 傅若山，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672249 Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem]<br /> <br /> * '''''Session 3: Machine Learning'''''<br /> # 孙珂，ACL 2024，[https://arxiv.org/abs/2406.02030 Multimodal Reasoning with Multimodal Knowledge Graph]<br /> # 王哲，ICML 2022，[https://proceedings.mlr.press/v162/paulus22a Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning]<br /> # 胡维军，CVPR 2024，[http://openaccess.thecvf.com/content/CVPR2024/html/Jia_Generative_Latent_Coding_for_Ultra-Low_Bitrate_Image_Compression_CVPR_2024_paper.html Generative Latent Coding for Ultra-Low Bitrate Image Compression]<br /> # 李星彤，KDD 2023，[https://dl.acm.org/doi/abs/10.1145/3580305.3599831 Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning]<br /> <br /> * '''''Session 4: Modeling theory and algorithms'''''<br /> # 王一宁，Applied Intelligence 2020，[https://link.springer.com/article/10.1007/s10489-020-02072-w A hybrid ant colony system algorithm for solving the ring star problem]<br /> # 许平登峰，ICMA 2022，[https://ieeexplore.ieee.org/abstract/document/9856100/ Social Distance Measuring Based on Monocular Vision]<br /> # 刘书奇，NeurIPS 2022，[https://arxiv.org/abs/2008.08844 Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks]<br /> # 顾瀚杰，NeuralIPS 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/271db9922b8d1f4dd7aaef84ed5ac703-Abstract-Conference.html Tree of Thoughts: Deliberate Problem Solving with Large Language Models]<br /> &lt;br&gt;<br /> '''Day 2: Apr. 17, 2025.'''<br /> ----<br /> * '''''Session 5: Security'''''<br /> # 刘文豪，S&amp;P 2023，[https://ieeexplore.ieee.org/abstract/document/10228892/ CoChain: High Concurrency Blockchain Sharding via Consensus on Consensus]<br /> # 朱钰立，TMC 2024，[https://ieeexplore.ieee.org/abstract/document/10432986/ Secret Key Generation Based on Manipulated Channel Measurement Matching]<br /> # 徐睿航，SigComm 2023，[https://dl.acm.org/doi/10.1145/3603269.3604874 NeoBFT: Accelerating Byzantine Fault Tolerance Using Authenticated In-Network Ordering]<br /> # 苏徐涛，Advances in Neural Information Processing Systems 2023，[https://proceedings.neurips.cc/paper_files/paper/2023/hash/0207c9ea9faf66c6e892c3fa3c167b75-Abstract-Conference.html Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training]<br /> <br /> * '''Session 6: Privacy'''<br /> # 周锦涛，SIGCOMM 2024，[https://dl.acm.org/doi/abs/10.1145/3651890.3672217 ConfMask: Enabling Privacy-Preserving Configuration Sharing via Anonymization]<br /> # 吴心淇，WWW 2024，[https://dl.acm.org/doi/abs/10.1145/3589334.3645386 SPRING: improving the throughput of sharding blockchain via deep reinforcement learning]<br /> # 刘梦颖，计算机学报 2023，[https://dl.ccf.org.cn/article/articleDetail.html?type=qkwz&amp;_ack=1&amp;id=6375068666660864 一种基于本地化差分隐私的网格聚类方法]<br /> # 杨若菡，计算机学报 2025，[https://www.cnki.com.cn/Article/CJFDTotal-JSJX20250321005.htm 面向隐私保护的用户评论基准数据集构建与大模型推理能力评估]<br /> <br /> * '''Session 7: Interesting topics'''<br /> # 农烨，AAAI 2023，[https://ojs.aaai.org/index.php/AAAI/article/view/25556 PDFormer: Propagation Delay-aware Dynamic Long-range Transformer for Traffic Flow Prediction]<br /> # 鲜沛宏，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621209/ A De-anonymization Attack Against Downloaders in Freenet]<br /> # 徐楠钧，CV-arXiv 2024，[https://arxiv.org/abs/2406.08801 Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation]<br /> # 刘睿哲，INFOCOM 2024，[https://ieeexplore.ieee.org/abstract/document/10621148/ VisFlow: Adaptive Content-Aware Video Analytics on Collaborative Cameras]<br /> <br /> <br /> ==课程要求(2024)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> ===报告安排===<br /> * 每个Session由Session chair花2分钟总结Session中的大致情况，包含几篇文章，做什么方面的，会议/期刊情况等。<br /> * 每位同学汇报5-6分钟<br /> * 问答环节1-2分钟<br /> * 说明：<br /> # 一次提问加2分口头报告分数（即总分0.6分），每人最多加3次（Chair默认加两次提问分）<br /> # 报告内容以问题为主，切忌太快跳入细节<br /> # 注意运用课堂内容，评价选题、评价论点、解析文章的骨架（1-3-9）<br /> <br /> ===报告顺序：===<br /> * '''Session 1: Mobile computing (16:20 - 16:50, Chair: 喻宣然)'''<br /> # 徐铮, FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices, ACM MobiCom, 2024.<br /> # 喻宣然, Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction, USENIX Security 2024.<br /> # 王子琛, Face Recognition In Harsh Conditions: An Acoustic Based Approach, ACM MobiSys 2024.<br /> # 龚晓路, EVLeSen: In-Vehicle Sensing with EV-Leaked Signal, ACM MobiCom 2024.<br /> <br /> * '''Session 2: Computer vision (1) (16:50 - 17:20, Chair: 张周睿)'''<br /> # 张周睿, Domain Adaptation for Image Dehazing, CVPR, 2020.<br /> # 王懿, Post-Training Quantization for Vison Transformer. NeurIPS 2021.<br /> # 王昕妮, A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement, IEEE Transactions on Cybernetics, 2017.<br /> # 王焜尧, End-to-end Object Detection with Transformers. ECCV, 2020.<br /> <br /> * '''Session 3: Interesting and Trending (17:20 - 17:50, Chair: 陈云辉)'''<br /> # 陈云辉, Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing, IEEE INFOCOM, 2023.<br /> # 李其睿, 从“网红”到“长红”：旅游公共服务吸引力与供给次序——基于抖音“淄博烧烤”话题的用户评论分析，消费经济，2024.<br /> # 孙权恩, Task Representations in Neural Networks Trained to Perform Many Cognitive Tasks. Nature neuroscience, 2019.<br /> # 黄城瑞, ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs, ICLR spotlight, 2024.<br /> <br /> * '''Session 4: Network systems (19:00 - 19:30, Chair: 李放波)'''<br /> # 李放波, DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics, ACM/IEEE ISCA 2024.<br /> # 张宇全, iStack: A General and Stateful Name-based Protocol Stack for Named Data Networking, USENIX NSDI, 2024.<br /> # 王建基, Triton: A Flexible Hardware Offloading Architecture for Accelerating Apsara vSwitch in Alibaba Cloud，ACM SIGCOMM, 2024.<br /> # 黄昌吉, FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform, ACM MobiCom, 2024.<br /> <br /> * '''Session 5: CV(2) and Machine learning (19:30 - 20:00, Chair: 李海龙)'''<br /> # 郑洋, Score-guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems, ICML, 2022.<br /> # 徐晗洋, Class-Specific Semantic Reconstruction for Open Set Recognition, IEEE TPAMI, 2023.<br /> # 林雅萍, CosFace: Large Margin Cosine Loss for Deep Face Recognition，IEEE CVPR, 2018.<br /> # 李海龙, 3D Gaussian Splatting for Real-Time Radiance Field Rendering, ACM SIGGRAPH 2023.<br /> <br /> * '''Session 6: Security and Efficiency (20:00 - 20:35, Chair: 曹郅杰)'''<br /> # 韩文昊, Off-Path TCP Sequence Number Inference Attack, IEEE S&amp;P, 2012.<br /> # 刘铮杨, Topology-aware Differential Privacy for Decentralized Image Classification，IEEE TNNLS，2022.<br /> # 韩慧麟, Efficient Secure Multiparty Computation of The Maximum and The Minimum，Advanced Engineering Sciences, 2023.<br /> # 曹郅杰, H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem，AAAI, 2023.<br /> # 徐灏阳, Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts, KDD, 2018.<br /> <br /> <br /> ==课程要求(2023)==<br /> 最终成绩 = 40%课程论文+30%平时成绩（含英文部分）+30%口头报告<br /> <br /> *平时成绩：包含3-4次随堂测验，其中3次最好成绩的平均值计为平时成绩。<br /> *口头报告：小组分享，互评<br /> *学术论文的要求：<br /> **字数≥1000<br /> **格式要求：<br /> ***题目<br /> ***作者排名<br /> ***论文亮点和不足（各列举不少于3条）<br /> ***摘要（本篇评论的摘要）<br /> ***简介/引言<br /> ***研究现状与难点分析<br /> ***研究思路及评价<br /> ***具体方案及评价<br /> ***实验及实验中最具说服力的部分分析<br /> ***结论及问题展望<br /> **自行选择论文进行评论<br /> --&gt;<br /> <br /> ===说明===<br /> *如果被发现超过3次缺课，则成绩为0.<br /> *如果发现任何形式抄袭，成绩为0.<br /> *论文提交日期2025.04.23 - 2025.04.30<br /> {{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=%E6%8B%9B%E7%94%9F&diff=3495 2026-03-04T06:08:30Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=招生说明<br /> |content=<br /> * 个人简历请发送至 zhaosheng@mobinets.org，随时接收简历，交流及录取过程在每年3月(考研)和7-9月(保研)。<br /> * 由于实验室日常教学科研工作较多，建议保研同学在7-9月邮件联系，考研同学在2-4月份联系，以免邮件被错过。<br /> &lt;!--* '''20250715更新'''：近期接收简历较多，如未及时收到回信，请联系其他老师。祝各位同学一切顺利！--&gt;<br /> }}<br /> &lt;!--<br /> &lt;div align=&quot;center&quot;&gt;<br /> &lt;br&gt;<br /> &lt;big&gt;''''''''另：复试程序保障了提前联系团队与复试能否通过完全没有关联，请各位报名同学认真准备学院复试。''''''''&lt;/big&gt;<br /> 参考：<br /> [http://yjsjy.uestc.edu.cn/gmis/jcsjgl/dsfc/index/#08 电子科大研招网导师列表], <br /> [http://www.scse.uestc.edu.cn/sz.jsp?urltype=tree.TreeTempUrl&amp;wbtreeid=1081 学院师资介绍]<br /> &lt;/div&gt;<br /> '''2022拔尖计划纳新在[[Resource:拔尖计划纳新|这里]]'''<br /> --&gt;<br /> ===='''申请链接'''====<br /> * [[Resource:拔尖计划纳新|'''拔尖计划纳新'''（面向本校本科生）]]<br /> * [[招生常见问答|'''必读信息''']]<br /> * [[招生申请流程|申请流程]]<br /> &lt;!-- * 和赵老师的[https://mobinets.cn/talk2zhiwei 小助理⛄]聊聊天 --&gt;<br /> <br /> ===='''团队简介'''====<br /> 团队主要研究方向包含泛在边缘计算和智能物联网系统。近五年在中国计算机学会(CCF)认定的A类期刊和会议及中科院认定的一区期刊上发表30余篇学术论文。团队成员承担中国国家自然基金、欧盟FP7项目、英国皇家学会、国家重点研发计划等国家级、省部级科研项目，并与华为、中移动等工业界企业具有良好的科研合作。实验室具有良好的硬件条件、严谨的科研氛围、融洽的师生关系，希望招收有志于在智慧物联网、智慧城市、未来网络演进等前沿课题有所建树的研究生和博士生，一起努力，共创未来。<br /> <br /> &lt;div align=&quot;center&quot;&gt;<br /> [[File:Team25.png|700px|link=]]<br /> [[File:humao.png|700px|link=]]<br /> &lt;/div&gt;<br /> <br /> &lt;!--<br /> &lt;gallery mode=&quot;slideshow&quot;&gt;<br /> File:humao.png|700px<br /> File:alumni.png|700px<br /> File:frontimg.png|700px<br /> &lt;/gallery&gt;<br /> --&gt;<br /> <br /> &lt;!--<br /> [[File:alumni.png|700px|link=]]<br /> [[File:frontimg.png|700px|link=]]<br /> --&gt;<br /> <br /> ===='''培养方式'''====<br /> 团队以学术创新为宗旨，对博士生和硕士生规划了不同的培养路线，确保学生和团队共同进步。<br /> <br /> ===== &gt;'''博士生培养'''=====<br /> (直博、硕博连读)<br /> [[File:phd.jpg|center|800px|link=]]<br /> ===== &gt;'''硕士生培养'''=====<br /> (分为科研与工程两类、研一及研二可择优转为硕博连读)<br /> [[File:ms.jpg|center|800px|link=]]<br /> <br /> &lt;br&gt;<br /> &lt;br&gt;<br /> ===='''毕业生去向'''====<br /> {{Former_members}}<br /> &lt;!--<br /> This page was last edited on {{REVISIONYEAR}}-{{REVISIONMONTH}}-{{REVISIONDAY}}.<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3494 2026-03-04T06:08:06Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;br&gt;<br /> &lt;!--教授、博导、国家级青年人才、四川省高层次人才、欧盟玛丽居里学者--&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> &lt;!-- * '''和我的[https://mobinets.cn/talk2zhiwei 小助理⛄]聊聊天''' --&gt;<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Data-driven Artificial Intelligence of Things, National Key Research and Development Program of China.<br /> * Key Technologies on Data Management for Drone Networks, Sichuan Natural Science Foundation of China.<br /> * Integrated Sensing for City-wide Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3493 2026-02-27T11:04:46Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;br&gt;<br /> &lt;!--教授、博导、国家级青年人才、四川省高层次人才、欧盟玛丽居里学者--&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> * '''和我的[https://mobinets.cn/talk2zhiwei 小助理⛄]聊聊天'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Data-driven Artificial Intelligence of Things, National Key Research and Development Program of China.<br /> * Key Technologies on Data Management for Drone Networks, Sichuan Natural Science Foundation of China.<br /> * Integrated Sensing for City-wide Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Tutorial&diff=3492 2026-02-09T10:52:52Z

<p>Zhiwei: </p> <hr /> <div>{{Note|We list tutorials for beginners to start research in MobiNetS. The tutorials will be updated continueously. }}<br /> <br /> List of tutorials: <br /> <br /> ==== General ====<br /> &lt;!--<br /> * [[Tutorial:Must_read|Must-read papers]]<br /> --&gt;<br /> * [[Tutorial:Find_papers|How to find papers]]<br /> * [[Tutorial:Reading|How to read efficiently]]<br /> * [[Tutorial: Writing|Start Academic Writing]]<br /> * [[Tutorial:Weekly_reports|How to write a logical and helpful report]]<br /> * [[Tutorial:Sentences|Beautiful sentences]]<br /> * [[Tutorial:Grammarly|Grammarly]]<br /> * [[Tutorial:Remote_Access|Remote access to servers and PCs]]<br /> <br /> ====Low-power Wireless and Embeded====<br /> * [[Tutorial:LoRa|LoRa]]<br /> * [[Tutorial:ZigBee|TinyOS/ZigBee]]<br /> * [[Tutorial:Arduino|Arduino]]<br /> * [[Tutorial:OpenWrt|OpenWrt]]<br /> * [[Tutorial:3DPrinter|3D Printer]]<br /> <br /> ==== Edge Computing ====<br /> * [[Tutorial:Edge_simulation|Matlab simulations]]<br /> * [[Tutorial:EdgeCloudSim|EdgeCloudSim]]<br /> * [[Tutorial:Federated_learning|Federated Learning]]<br /> <br /> ==== Mobile ====<br /> * [[Tutorial:Android_phones|Android phones]]<br /> * [[Tutorial:WearOS_wearables|WearOS devices]]<br /> * [[Tutorial:Path_plan|Path Plan]]<br /> * [https://webvpn.uestc.edu.cn/http-53502/77726476706e69737468656265737421a1a510d2736826012859c7fecd04/ testwork]</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Tutorial&diff=3491 2026-02-01T08:42:55Z

<p>Zhiwei: </p> <hr /> <div>{{Note|We list tutorials for beginners to start research in MobiNetS. The tutorials will be updated continueously. }}<br /> <br /> List of tutorials: <br /> <br /> ==== General ====<br /> &lt;!--<br /> * [[Tutorial:Must_read|Must-read papers]]<br /> --&gt;<br /> * [[Tutorial:Find_papers|How to find papers]]<br /> * [[Tutorial:Reading|How to read efficiently]]<br /> * [[Tutorial: Writing|Start Academic Writing]]<br /> * [[Tutorial:Weekly_reports|How to write a logical and helpful report]]<br /> * [[Tutorial:Sentences|Beautiful sentences]]<br /> * [[Tutorial:Grammarly|Grammarly]]<br /> * [[Tutorial:Remote_Access|Remote access to servers and PCs]]<br /> <br /> ====Low-power Wireless and Embeded====<br /> * [[Tutorial:LoRa|LoRa]]<br /> * [[Tutorial:ZigBee|TinyOS/ZigBee]]<br /> * [[Tutorial:Arduino|Arduino]]<br /> * [[Tutorial:OpenWrt|OpenWrt]]<br /> * [[Tutorial:3DPrinter|3D Printer]]<br /> <br /> ==== Edge Computing ====<br /> * [[Tutorial:Edge_simulation|Matlab simulations]]<br /> * [[Tutorial:EdgeCloudSim|EdgeCloudSim]]<br /> * [[Tutorial:Federated_learning|Federated Learning]]<br /> <br /> ==== Mobile ====<br /> * [[Tutorial:Android_phones|Android phones]]<br /> * [[Tutorial:WearOS_wearables|WearOS devices]]<br /> * [[Tutorial:Path_plan|Path Plan]]<br /> * [http://121.48.161.251:53502/ testwork]</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3490 2026-01-30T02:51:20Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2026-01-30 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = LoRa technology promises to enable Internet of Things applications over large geographical areas. However, its performance is often hampered by poor channel quality in urban environments, where blockage and multipath effects are prevalent. Our study uncovers that a slight shift in the position or attitude of the receiving antenna can substantially improve the received signal quality. This phenomenon can be attributed to the rich multipath characteristics of wireless signal propagation in urban environments, wherein even small antenna movement can alter the dominant signal path or reduce the polarization angular difference between transceivers. Leveraging these key observations, we propose and implement MoLoRa, an intelligent mobile antenna system designed to enhance LoRa packet reception. At its core, MoLoRa represents the position and attitude of an antenna as a state and employs a statistical optimization method to search for states that offer optimal signal quality efficiently. Through extensive evaluation, we demonstrate that MoLoRa achieves a maximum Signal-to-Noise Ratio (SNR) gain of 13 dB in a few attempts, enabling formerly problematic blind spots to reconnect and strengthening links for other nodes.<br /> |confname =SenSys'25<br /> |link = https://dl.acm.org/doi/10.1145/3715014.3722075<br /> |title= MoLoRa: Intelligent Mobile Antenna System for Enhanced LoRa Reception in Urban Environments<br /> |speaker=Kai Chen<br /> |date=2026-1-30<br /> }}<br /> {{Latest_seminar<br /> |abstract =Large language models (LLMs) achieve superior performance in generative tasks. However, due to the natural gap between language model generation and structured information extraction in three dimensions: task type, output format, and modeling granularity, they often fall short in structured information extraction, a crucial capability for effective data utilization on the web. In this paper, we define the generation process of the language model as the controllable state transition, aligning the generation and extraction processes to ensure the integrity of the output structure and adapt to the goals of the information extraction task. Furthermore, we propose the Structure2Text decider to help the language model understand the fine-grained extraction information, which converts the structured output into natural language and makes state decisions, thereby focusing on the task-specific information kernels, and alleviating language model hallucinations and incorrect content generation. We conduct extensive experiments and detailed analyses on myriad information extraction tasks, including named entity recognition, relation extraction, and event argument extraction. Our method not only achieves significant performance improvements but also considerably enhances the model's capability to generate precise and relevant content, making the extracted content easy to parse.<br /> |confname =WWW'25<br /> |link = https://dl.acm.org/doi/abs/10.1145/3696410.3714571<br /> |title= Bridging the Gap: Aligning Language Model Generation with Structured Information Extraction via Controllable State Transition<br /> |speaker=Daobin<br /> |date=2026-1-30<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3486 2026-01-28T01:35:44Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;br&gt;<br /> &lt;!--教授、博导、国家级青年人才、四川省高层次人才、欧盟玛丽居里学者--&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> * '''和我的[https://mobinets.cn/talk2zhiwei 数字分身⛄]聊聊天'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Data-driven Artificial Intelligence of Things, National Key Research and Development Program of China.<br /> * Key Technologies on Data Management for Drone Networks, Sichuan Natural Science Foundation of China.<br /> * Integrated Sensing for City-wide Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=%E6%8B%9B%E7%94%9F&diff=3485 2026-01-27T02:41:23Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=招生说明<br /> |content=<br /> * 个人简历请发送至 zhaosheng@mobinets.org，随时接收简历，交流及录取过程在每年3月(考研)和7-9月(保研)。<br /> * 由于实验室日常教学科研工作较多，建议保研同学在7-9月邮件联系，考研同学在2-4月份联系，以免邮件被错过。<br /> &lt;!--* '''20250715更新'''：近期接收简历较多，如未及时收到回信，请联系其他老师。祝各位同学一切顺利！--&gt;<br /> }}<br /> &lt;!--<br /> &lt;div align=&quot;center&quot;&gt;<br /> &lt;br&gt;<br /> &lt;big&gt;''''''''另：复试程序保障了提前联系团队与复试能否通过完全没有关联，请各位报名同学认真准备学院复试。''''''''&lt;/big&gt;<br /> 参考：<br /> [http://yjsjy.uestc.edu.cn/gmis/jcsjgl/dsfc/index/#08 电子科大研招网导师列表], <br /> [http://www.scse.uestc.edu.cn/sz.jsp?urltype=tree.TreeTempUrl&amp;wbtreeid=1081 学院师资介绍]<br /> &lt;/div&gt;<br /> '''2022拔尖计划纳新在[[Resource:拔尖计划纳新|这里]]'''<br /> --&gt;<br /> ===='''申请链接'''====<br /> * [[Resource:拔尖计划纳新|'''拔尖计划纳新'''（面向本校本科生）]]<br /> * [[招生常见问答|'''必读信息''']]<br /> * [[招生申请流程|申请流程]]<br /> * 和赵老师的[https://mobinets.cn/talk2zhiwei 数字分身⛄]聊聊天<br /> <br /> ===='''团队简介'''====<br /> 团队主要研究方向包含泛在边缘计算和智能物联网系统。近五年在中国计算机学会(CCF)认定的A类期刊和会议及中科院认定的一区期刊上发表30余篇学术论文。团队成员承担中国国家自然基金、欧盟FP7项目、英国皇家学会、国家重点研发计划等国家级、省部级科研项目，并与华为、中移动等工业界企业具有良好的科研合作。实验室具有良好的硬件条件、严谨的科研氛围、融洽的师生关系，希望招收有志于在智慧物联网、智慧城市、未来网络演进等前沿课题有所建树的研究生和博士生，一起努力，共创未来。<br /> <br /> &lt;div align=&quot;center&quot;&gt;<br /> [[File:Team25.png|700px|link=]]<br /> [[File:humao.png|700px|link=]]<br /> &lt;/div&gt;<br /> <br /> &lt;!--<br /> &lt;gallery mode=&quot;slideshow&quot;&gt;<br /> File:humao.png|700px<br /> File:alumni.png|700px<br /> File:frontimg.png|700px<br /> &lt;/gallery&gt;<br /> --&gt;<br /> <br /> &lt;!--<br /> [[File:alumni.png|700px|link=]]<br /> [[File:frontimg.png|700px|link=]]<br /> --&gt;<br /> <br /> ===='''培养方式'''====<br /> 团队以学术创新为宗旨，对博士生和硕士生规划了不同的培养路线，确保学生和团队共同进步。<br /> <br /> ===== &gt;'''博士生培养'''=====<br /> (直博、硕博连读)<br /> [[File:phd.jpg|center|800px|link=]]<br /> ===== &gt;'''硕士生培养'''=====<br /> (分为科研与工程两类、研一及研二可择优转为硕博连读)<br /> [[File:ms.jpg|center|800px|link=]]<br /> <br /> &lt;br&gt;<br /> &lt;br&gt;<br /> ===='''毕业生去向'''====<br /> {{Former_members}}<br /> &lt;!--<br /> This page was last edited on {{REVISIONYEAR}}-{{REVISIONMONTH}}-{{REVISIONDAY}}.<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3484 2026-01-27T02:41:05Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> * '''和我的[https://mobinets.cn/talk2zhiwei 数字分身⛄]聊聊天'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Integrated Sensing for Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=%E6%8B%9B%E7%94%9F&diff=3483 2026-01-25T02:09:09Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=招生说明<br /> |content=<br /> * 个人简历请发送至 zhaosheng@mobinets.org，随时接收简历，交流及录取过程在每年3月(考研)和7-9月(保研)。<br /> * 由于实验室日常教学科研工作较多，建议保研同学在7-9月邮件联系，考研同学在2-4月份联系，以免邮件被错过。<br /> &lt;!--* '''20250715更新'''：近期接收简历较多，如未及时收到回信，请联系其他老师。祝各位同学一切顺利！--&gt;<br /> }}<br /> &lt;!--<br /> &lt;div align=&quot;center&quot;&gt;<br /> &lt;br&gt;<br /> &lt;big&gt;''''''''另：复试程序保障了提前联系团队与复试能否通过完全没有关联，请各位报名同学认真准备学院复试。''''''''&lt;/big&gt;<br /> 参考：<br /> [http://yjsjy.uestc.edu.cn/gmis/jcsjgl/dsfc/index/#08 电子科大研招网导师列表], <br /> [http://www.scse.uestc.edu.cn/sz.jsp?urltype=tree.TreeTempUrl&amp;wbtreeid=1081 学院师资介绍]<br /> &lt;/div&gt;<br /> '''2022拔尖计划纳新在[[Resource:拔尖计划纳新|这里]]'''<br /> --&gt;<br /> ===='''申请链接'''====<br /> * [[Resource:拔尖计划纳新|'''拔尖计划纳新'''（面向本校本科生）]]<br /> * [[招生常见问答|'''必读信息''']]<br /> * [[招生申请流程|申请流程]]<br /> * 和赵老师的[https://mns.uestc.cn/talk2zhiwei 数字分身⛄]聊聊天<br /> <br /> ===='''团队简介'''====<br /> 团队主要研究方向包含泛在边缘计算和智能物联网系统。近五年在中国计算机学会(CCF)认定的A类期刊和会议及中科院认定的一区期刊上发表30余篇学术论文。团队成员承担中国国家自然基金、欧盟FP7项目、英国皇家学会、国家重点研发计划等国家级、省部级科研项目，并与华为、中移动等工业界企业具有良好的科研合作。实验室具有良好的硬件条件、严谨的科研氛围、融洽的师生关系，希望招收有志于在智慧物联网、智慧城市、未来网络演进等前沿课题有所建树的研究生和博士生，一起努力，共创未来。<br /> <br /> &lt;div align=&quot;center&quot;&gt;<br /> [[File:Team25.png|700px|link=]]<br /> [[File:humao.png|700px|link=]]<br /> &lt;/div&gt;<br /> <br /> &lt;!--<br /> &lt;gallery mode=&quot;slideshow&quot;&gt;<br /> File:humao.png|700px<br /> File:alumni.png|700px<br /> File:frontimg.png|700px<br /> &lt;/gallery&gt;<br /> --&gt;<br /> <br /> &lt;!--<br /> [[File:alumni.png|700px|link=]]<br /> [[File:frontimg.png|700px|link=]]<br /> --&gt;<br /> <br /> ===='''培养方式'''====<br /> 团队以学术创新为宗旨，对博士生和硕士生规划了不同的培养路线，确保学生和团队共同进步。<br /> <br /> ===== &gt;'''博士生培养'''=====<br /> (直博、硕博连读)<br /> [[File:phd.jpg|center|800px|link=]]<br /> ===== &gt;'''硕士生培养'''=====<br /> (分为科研与工程两类、研一及研二可择优转为硕博连读)<br /> [[File:ms.jpg|center|800px|link=]]<br /> <br /> &lt;br&gt;<br /> &lt;br&gt;<br /> ===='''毕业生去向'''====<br /> {{Former_members}}<br /> &lt;!--<br /> This page was last edited on {{REVISIONYEAR}}-{{REVISIONMONTH}}-{{REVISIONDAY}}.<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3482 2026-01-25T02:08:25Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> * '''和我的[https://mns.uestc.cn/talk2zhiwei 数字分身⛄]聊聊天'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Integrated Sensing for Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=%E6%8B%9B%E7%94%9F&diff=3481 2026-01-24T10:35:34Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=招生说明<br /> |content=<br /> * 个人简历请发送至 zhaosheng@mobinets.org，随时接收简历，交流及录取过程在每年3月(考研)和7-9月(保研)。<br /> * 由于实验室日常教学科研工作较多，建议保研同学在7-9月邮件联系，考研同学在2-4月份联系，以免邮件被错过。<br /> &lt;!--* '''20250715更新'''：近期接收简历较多，如未及时收到回信，请联系其他老师。祝各位同学一切顺利！--&gt;<br /> }}<br /> &lt;!--<br /> &lt;div align=&quot;center&quot;&gt;<br /> &lt;br&gt;<br /> &lt;big&gt;''''''''另：复试程序保障了提前联系团队与复试能否通过完全没有关联，请各位报名同学认真准备学院复试。''''''''&lt;/big&gt;<br /> 参考：<br /> [http://yjsjy.uestc.edu.cn/gmis/jcsjgl/dsfc/index/#08 电子科大研招网导师列表], <br /> [http://www.scse.uestc.edu.cn/sz.jsp?urltype=tree.TreeTempUrl&amp;wbtreeid=1081 学院师资介绍]<br /> &lt;/div&gt;<br /> '''2022拔尖计划纳新在[[Resource:拔尖计划纳新|这里]]'''<br /> --&gt;<br /> ===='''申请链接'''====<br /> * [[Resource:拔尖计划纳新|'''拔尖计划纳新'''（面向本校本科生）]]<br /> * [[招生常见问答|'''必读信息''']]<br /> * [[招生申请流程|申请流程]]<br /> * 和赵老师的[https://mns.uestc.cn/resource/talk2zhiwei 数字分身⛄]聊聊天<br /> <br /> ===='''团队简介'''====<br /> 团队主要研究方向包含泛在边缘计算和智能物联网系统。近五年在中国计算机学会(CCF)认定的A类期刊和会议及中科院认定的一区期刊上发表30余篇学术论文。团队成员承担中国国家自然基金、欧盟FP7项目、英国皇家学会、国家重点研发计划等国家级、省部级科研项目，并与华为、中移动等工业界企业具有良好的科研合作。实验室具有良好的硬件条件、严谨的科研氛围、融洽的师生关系，希望招收有志于在智慧物联网、智慧城市、未来网络演进等前沿课题有所建树的研究生和博士生，一起努力，共创未来。<br /> <br /> &lt;div align=&quot;center&quot;&gt;<br /> [[File:Team25.png|700px|link=]]<br /> [[File:humao.png|700px|link=]]<br /> &lt;/div&gt;<br /> <br /> &lt;!--<br /> &lt;gallery mode=&quot;slideshow&quot;&gt;<br /> File:humao.png|700px<br /> File:alumni.png|700px<br /> File:frontimg.png|700px<br /> &lt;/gallery&gt;<br /> --&gt;<br /> <br /> &lt;!--<br /> [[File:alumni.png|700px|link=]]<br /> [[File:frontimg.png|700px|link=]]<br /> --&gt;<br /> <br /> ===='''培养方式'''====<br /> 团队以学术创新为宗旨，对博士生和硕士生规划了不同的培养路线，确保学生和团队共同进步。<br /> <br /> ===== &gt;'''博士生培养'''=====<br /> (直博、硕博连读)<br /> [[File:phd.jpg|center|800px|link=]]<br /> ===== &gt;'''硕士生培养'''=====<br /> (分为科研与工程两类、研一及研二可择优转为硕博连读)<br /> [[File:ms.jpg|center|800px|link=]]<br /> <br /> &lt;br&gt;<br /> &lt;br&gt;<br /> ===='''毕业生去向'''====<br /> {{Former_members}}<br /> &lt;!--<br /> This page was last edited on {{REVISIONYEAR}}-{{REVISIONMONTH}}-{{REVISIONDAY}}.<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3480 2026-01-24T10:32:37Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> * '''和我的[https://mns.uestc.cn/resource/talk2zhiwei 数字分身⛄]聊聊天'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Integrated Sensing for Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3479 2026-01-24T10:31:52Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> * '''和我的[[https://mns.uestc.cn/resource/talk2zhiwei|数字分身⛄]]聊聊天'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Integrated Sensing for Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=ZhiweiTalk&diff=3478 2026-01-23T11:32:31Z

<p>Zhiwei: Replaced content with &quot;&lt;html&gt; &lt;iframe src=&quot;https://mns.uestc.cn/resource/talk2zhiwei.html&quot; width=&quot;100%&quot; frameborder=&quot;0&quot;&gt;&lt;/iframe&gt; &lt;/html&gt;&quot;</p> <hr /> <div>&lt;html&gt;<br /> &lt;iframe src=&quot;https://mns.uestc.cn/resource/talk2zhiwei.html&quot; width=&quot;100%&quot; frameborder=&quot;0&quot;&gt;&lt;/iframe&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=ZhiweiTalk&diff=3477 2026-01-23T11:25:55Z

<p>Zhiwei: Created page with &quot;&lt;html lang=&quot;zh-CN&quot;&gt; &lt;head&gt; &lt;meta charset=&quot;UTF-8&quot;&gt; &lt;meta name=&quot;viewport&quot; content=&quot;width=device-width, initial-scale=1.0&quot;&gt; &lt;title&gt;赵老师的数字分身&lt;/title&gt;...&quot;</p> <hr /> <div>&lt;html lang=&quot;zh-CN&quot;&gt;<br /> &lt;head&gt;<br /> &lt;meta charset=&quot;UTF-8&quot;&gt;<br /> &lt;meta name=&quot;viewport&quot; content=&quot;width=device-width, initial-scale=1.0&quot;&gt;<br /> &lt;title&gt;赵老师的数字分身&lt;/title&gt;<br /> &lt;style&gt;<br /> /* 仅保留核心样式，移除背景色 */<br /> .dt-container {<br /> max-width: 800px;<br /> margin: 0 auto;<br /> background: white;<br /> border-radius: 15px;<br /> box-shadow: 0 10px 30px rgba(0,0,0,0.2);<br /> overflow: hidden;<br /> font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;<br /> }<br /> <br /> .dt-header {<br /> background: linear-gradient(135deg, #4a90e2 0%, #667eea 100%);<br /> color: white;<br /> padding: 20px;<br /> text-align: center;<br /> }<br /> <br /> .dt-header h1 {<br /> font-size: 24px;<br /> margin-bottom: 5px;<br /> }<br /> <br /> .dt-header p {<br /> font-size: 14px;<br /> opacity: 0.9;<br /> }<br /> <br /> .dt-chat-area {<br /> height: 400px;<br /> overflow-y: auto;<br /> padding: 20px;<br /> background: #f8f9fa;<br /> }<br /> <br /> .dt-message {<br /> margin-bottom: 15px;<br /> padding: 12px 16px;<br /> border-radius: 12px;<br /> max-width: 80%;<br /> word-wrap: break-word;<br /> line-height: 1.5;<br /> }<br /> <br /> .dt-user-message {<br /> background: linear-gradient(135deg, #4a90e2 0%, #667eea 100%);<br /> color: white;<br /> margin-left: auto;<br /> text-align: right;<br /> }<br /> <br /> .dt-bot-message {<br /> background: #e9ecef;<br /> color: #333;<br /> margin-right: auto;<br /> }<br /> <br /> .dt-input-area {<br /> padding: 20px;<br /> background: white;<br /> border-top: 1px solid #eee;<br /> display: flex;<br /> gap: 10px;<br /> }<br /> <br /> .dt-message-input {<br /> flex: 1;<br /> padding: 12px 15px;<br /> border: 2px solid #e1e5e9;<br /> border-radius: 25px;<br /> resize: none;<br /> height: 50px;<br /> font-size: 14px;<br /> transition: border-color 0.3s;<br /> }<br /> <br /> .dt-message-input:focus {<br /> outline: none;<br /> border-color: #4a90e2;<br /> box-shadow: 0 0 0 3px rgba(74, 144, 226, 0.1);<br /> }<br /> <br /> .dt-button-group {<br /> display: flex;<br /> gap: 10px;<br /> }<br /> <br /> .dt-send-button, .dt-save-button {<br /> padding: 12px 20px;<br /> border: none;<br /> border-radius: 25px;<br /> cursor: pointer;<br /> font-size: 14px;<br /> font-weight: 500;<br /> transition: transform 0.2s, box-shadow 0.2s;<br /> }<br /> <br /> .dt-send-button {<br /> background: linear-gradient(135deg, #4a90e2 0%, #667eea 100%);<br /> color: white;<br /> }<br /> <br /> .dt-save-button {<br /> background: linear-gradient(135deg, #28a745 0%, #20c997 100%);<br /> color: white;<br /> }<br /> <br /> .dt-send-button:hover, .dt-save-button:hover {<br /> transform: translateY(-2px);<br /> box-shadow: 0 4px 12px rgba(0,0,0,0.15);<br /> }<br /> <br /> .dt-send-button:active, .dt-save-button:active {<br /> transform: translateY(0);<br /> }<br /> <br /> .dt-typing-indicator {<br /> display: inline-block;<br /> padding: 12px 16px;<br /> background: #e9ecef;<br /> border-radius: 12px;<br /> font-style: italic;<br /> color: #666;<br /> }<br /> <br /> .dt-status-bar {<br /> background: #f8f9fa;<br /> padding: 10px 20px;<br /> border-top: 1px solid #eee;<br /> font-size: 12px;<br /> color: #666;<br /> text-align: center;<br /> }<br /> <br /> .dt-welcome-message {<br /> text-align: center;<br /> color: #666;<br /> font-style: italic;<br /> padding: 20px;<br /> }<br /> <br /> /* Markdown 样式 */<br /> .markdown-content {<br /> line-height: 1.6;<br /> }<br /> <br /> .markdown-content h1,<br /> .markdown-content h2,<br /> .markdown-content h3 {<br /> margin: 10px 0 5px 0;<br /> font-weight: bold;<br /> color: #333;<br /> }<br /> <br /> .markdown-content h1 {<br /> font-size: 1.5em;<br /> border-bottom: 1px solid #eee;<br /> padding-bottom: 5px;<br /> }<br /> <br /> .markdown-content h2 {<br /> font-size: 1.3em;<br /> }<br /> <br /> .markdown-content h3 {<br /> font-size: 1.1em;<br /> }<br /> <br /> .markdown-content p {<br /> margin: 8px 0;<br /> }<br /> <br /> .markdown-content ul,<br /> .markdown-content ol {<br /> margin: 8px 0;<br /> padding-left: 20px;<br /> }<br /> <br /> .markdown-content li {<br /> margin: 4px 0;<br /> }<br /> <br /> .markdown-content strong {<br /> font-weight: bold;<br /> }<br /> <br /> .markdown-content em {<br /> font-style: italic;<br /> }<br /> <br /> .markdown-content code {<br /> background: #f1f1f1;<br /> padding: 2px 4px;<br /> border-radius: 3px;<br /> font-family: monospace;<br /> font-size: 0.9em;<br /> }<br /> <br /> .markdown-content pre {<br /> background: #f8f8f8;<br /> padding: 10px;<br /> border-radius: 5px;<br /> overflow-x: auto;<br /> margin: 10px 0;<br /> }<br /> <br /> .markdown-content pre code {<br /> background: none;<br /> padding: 0;<br /> }<br /> <br /> .markdown-content blockquote {<br /> border-left: 3px solid #ccc;<br /> padding-left: 10px;<br /> margin: 10px 0;<br /> color: #666;<br /> font-style: italic;<br /> }<br /> <br /> .markdown-content a {<br /> color: #4a90e2;<br /> text-decoration: none;<br /> }<br /> <br /> .markdown-content a:hover {<br /> text-decoration: underline;<br /> }<br /> <br /> @media (max-width: 600px) {<br /> .dt-container {<br /> margin: 10px;<br /> border-radius: 10px;<br /> }<br /> <br /> .dt-chat-area {<br /> height: 300px;<br /> }<br /> <br /> .dt-message {<br /> max-width: 90%;<br /> }<br /> <br /> .dt-input-area {<br /> flex-direction: column;<br /> }<br /> <br /> .dt-button-group {<br /> flex-direction: row;<br /> }<br /> }<br /> &lt;/style&gt;<br /> &lt;/head&gt;<br /> &lt;body&gt;<br /> &lt;!-- 这个容器可以嵌入到其他网页中 --&gt;<br /> &lt;div class=&quot;dt-container&quot;&gt;<br /> &lt;div class=&quot;dt-header&quot;&gt;<br /> &lt;h1&gt;🤖 赵老师的数字分身&lt;/h1&gt;<br /> &lt;p&gt;由于学校网络管理，偶遇重大节日或特殊日期时可能无法回答，请谅解~&lt;/p&gt;<br /> &lt;/div&gt;<br /> <br /> &lt;div class=&quot;dt-chat-area&quot; id=&quot;dt-chat-messages&quot;&gt;<br /> &lt;div class=&quot;dt-welcome-message&quot;&gt;<br /> 正在连接服务器...<br /> &lt;/div&gt;<br /> &lt;/div&gt;<br /> <br /> &lt;div class=&quot;dt-input-area&quot;&gt;<br /> &lt;textarea class=&quot;dt-message-input&quot; id=&quot;dt-message-input&quot; placeholder=&quot;请输入您的问题...&quot;&gt;&lt;/textarea&gt;<br /> &lt;div class=&quot;dt-button-group&quot;&gt;<br /> &lt;button class=&quot;dt-send-button&quot; id=&quot;dt-send-button&quot;&gt;发送&lt;/button&gt;<br /> &lt;button class=&quot;dt-save-button&quot; id=&quot;dt-save-button&quot;&gt;保存对话&lt;/button&gt;<br /> &lt;/div&gt;<br /> &lt;/div&gt;<br /> <br /> &lt;div class=&quot;dt-status-bar&quot; id=&quot;dt-status-bar&quot;&gt;<br /> &lt;span id=&quot;dt-connection-status&quot;&gt;正在初始化...&lt;/span&gt;<br /> &lt;/div&gt;<br /> &lt;/div&gt;<br /> <br /> &lt;script&gt;<br /> // 获取配置信息，允许通过属性传入<br /> const container = document.querySelector('.dt-container');<br /> const backendUrl = container.dataset.backendUrl || 'https://mns.uestc.cn/vs';<br /> const knowledgeBase = container.dataset.knowledgeBase || 'default'; // 可指定知识库<br /> <br /> document.addEventListener('DOMContentLoaded', function() {<br /> const chatMessages = document.getElementById('dt-chat-messages');<br /> const messageInput = document.getElementById('dt-message-input');<br /> const sendButton = document.getElementById('dt-send-button');<br /> const saveButton = document.getElementById('dt-save-button');<br /> const connectionStatus = document.getElementById('dt-connection-status');<br /> <br /> // 生成唯一的会话ID<br /> const sessionId = 'session_' + Date.now() + '_' + Math.random().toString(36).substr(2, 9);<br /> <br /> // 简单的Markdown解析函数<br /> function renderMarkdown(text) {<br /> // 替换标题<br /> text = text.replace(/^### (.*$)/gim, '&lt;h3&gt;$1&lt;/h3&gt;');<br /> text = text.replace(/^## (.*$)/gim, '&lt;h2&gt;$1&lt;/h2&gt;');<br /> text = text.replace(/^# (.*$)/gim, '&lt;h1&gt;$1&lt;/h1&gt;');<br /> <br /> // 替换粗体和斜体<br /> text = text.replace(/\*\*(.*?)\*\*/g, '&lt;strong&gt;$1&lt;/strong&gt;');<br /> text = text.replace(/\*(.*?)\*/g, '&lt;em&gt;$1&lt;/em&gt;');<br /> <br /> // 替换行内代码<br /> text = text.replace(/`(.*?)`/g, '&lt;code&gt;$1&lt;/code&gt;');<br /> <br /> // 替换链接<br /> text = text.replace(/\[(.*?)\]\((.*?)\)/g, '&lt;a href=&quot;$2&quot; target=&quot;_blank&quot;&gt;$1&lt;/a&gt;');<br /> <br /> // 替换引用<br /> text = text.replace(/^&gt; (.*$)/gim, '&lt;blockquote&gt;$1&lt;/blockquote&gt;');<br /> <br /> // 替换列表<br /> text = text.replace(/^\- (.*$)/gim, '&lt;li&gt;$1&lt;/li&gt;');<br /> text = text.replace(/^\* (.*$)/gim, '&lt;li&gt;$1&lt;/li&gt;');<br /> <br /> // 将连续的&lt;li&gt;包装到&lt;ul&gt;中<br /> text = text.replace(/(&lt;li&gt;.*&lt;\/li&gt;)/gs, '&lt;ul&gt;$1&lt;/ul&gt;');<br /> <br /> // 替换换行符为&lt;p&gt;标签<br /> text = text.replace(/\n\s*\n/g, '&lt;/p&gt;&lt;p&gt;');<br /> <br /> // 包装剩余文本到&lt;p&gt;标签中<br /> text = '&lt;p&gt;' + text + '&lt;/p&gt;';<br /> <br /> // 清理多余的&lt;p&gt;标签<br /> text = text.replace(/&lt;p&gt;\s*&lt;\/p&gt;/g, '');<br /> <br /> return text;<br /> }<br /> <br /> // 首次连接：发送&quot;欢迎接入&quot;获取欢迎信息<br /> async function initializeConnection() {<br /> try {<br /> connectionStatus.textContent = '正在初始化...';<br /> connectionStatus.style.color = '#ffc107';<br /> <br /> const response = await fetch(`${backendUrl}/query`, {<br /> method: 'POST',<br /> headers: {<br /> 'Content-Type': 'application/json'<br /> },<br /> body: JSON.stringify({ <br /> query: &quot;欢迎接入&quot;,<br /> session_id: sessionId,<br /> knowledge_base: knowledgeBase<br /> })<br /> });<br /> <br /> if (response.ok) {<br /> const data = await response.json();<br /> if (data.response) {<br /> // 成功连接，显示欢迎信息<br /> connectionStatus.textContent = '连接正常';<br /> connectionStatus.style.color = '#28a745';<br /> <br /> // 清空欢迎消息并显示欢迎信息<br /> chatMessages.innerHTML = '';<br /> addMessage(data.response, 'bot');<br /> return true;<br /> }<br /> }<br /> <br /> connectionStatus.textContent = '连接异常';<br /> connectionStatus.style.color = '#dc3545';<br /> return false;<br /> } catch (error) {<br /> console.error('初始化连接失败:', error);<br /> connectionStatus.textContent = '连接失败';<br /> connectionStatus.style.color = '#dc3545';<br /> return false;<br /> }<br /> }<br /> <br /> // 定期连接测试（不返回消息，只检查连接状态）<br /> async function testConnection() {<br /> try {<br /> const response = await fetch(`${backendUrl}/query`, {<br /> method: 'POST',<br /> headers: {<br /> 'Content-Type': 'application/json'<br /> },<br /> body: JSON.stringify({ <br /> query: &quot;连接测试&quot;,<br /> session_id: sessionId,<br /> knowledge_base: knowledgeBase<br /> })<br /> });<br /> <br /> if (response.ok) {<br /> const data = await response.json();<br /> // 连接测试只检查状态，不显示消息<br /> if (data.response === &quot;pong&quot;) {<br /> connectionStatus.textContent = '连接正常';<br /> connectionStatus.style.color = '#28a745';<br /> return true;<br /> }<br /> }<br /> <br /> connectionStatus.textContent = '连接异常';<br /> connectionStatus.style.color = '#dc3545';<br /> return false;<br /> } catch (error) {<br /> console.error('连接测试失败:', error);<br /> connectionStatus.textContent = '连接失败';<br /> connectionStatus.style.color = '#dc3545';<br /> return false;<br /> }<br /> }<br /> <br /> // 添加消息到聊天记录<br /> function addMessage(text, sender) {<br /> const messageDiv = document.createElement('div');<br /> messageDiv.className = `dt-message dt-${sender}-message`;<br /> <br /> // 如果是机器人消息，应用Markdown渲染<br /> if (sender === 'bot') {<br /> messageDiv.innerHTML = `&lt;div class=&quot;markdown-content&quot;&gt;${renderMarkdown(text)}&lt;/div&gt;`;<br /> } else {<br /> // 用户消息直接显示<br /> messageDiv.textContent = text;<br /> }<br /> <br /> chatMessages.appendChild(messageDiv);<br /> <br /> // 自动滚动到底部<br /> chatMessages.scrollTop = chatMessages.scrollHeight;<br /> }<br /> <br /> // 发送消息<br /> async function sendMessage() {<br /> const message = messageInput.value.trim();<br /> if (!message) return;<br /> <br /> // 添加用户消息<br /> addMessage(message, 'user');<br /> messageInput.value = '';<br /> <br /> // 显示打字指示器<br /> const typingIndicator = document.createElement('div');<br /> typingIndicator.className = 'dt-message dt-bot-message';<br /> typingIndicator.innerHTML = '&lt;div class=&quot;dt-typing-indicator&quot;&gt;正在思考...&lt;/div&gt;';<br /> chatMessages.appendChild(typingIndicator);<br /> chatMessages.scrollTop = chatMessages.scrollHeight;<br /> <br /> try {<br /> const response = await fetch(`${backendUrl}/query`, {<br /> method: 'POST',<br /> headers: {<br /> 'Content-Type': 'application/json'<br /> },<br /> body: JSON.stringify({ <br /> query: message,<br /> session_id: sessionId,<br /> knowledge_base: knowledgeBase<br /> })<br /> });<br /> <br /> const data = await response.json();<br /> <br /> // 移除打字指示器<br /> chatMessages.removeChild(typingIndicator);<br /> <br /> if (data.response) {<br /> addMessage(data.response, 'bot');<br /> } else {<br /> addMessage('抱歉，服务器返回了错误信息。', 'bot');<br /> }<br /> } catch (error) {<br /> console.error('Error:', error);<br /> chatMessages.removeChild(typingIndicator);<br /> addMessage('抱歉，连接服务器失败: ' + error.message, 'bot');<br /> }<br /> }<br /> <br /> // 保存对话历史<br /> function saveChatHistory() {<br /> const messages = chatMessages.querySelectorAll('.dt-message');<br /> let historyText = `数字分身对话历史\n${new Date().toLocaleString()}\n知识库: ${knowledgeBase}\n会话ID: ${sessionId}\n\n`;<br /> <br /> messages.forEach(msg =&gt; {<br /> if (msg.classList.contains('dt-user-message')) {<br /> historyText += `用户: ${msg.textContent}\n`;<br /> } else if (msg.classList.contains('dt-bot-message') &amp;&amp; !msg.querySelector('.dt-typing-indicator')) {<br /> historyText += `数字分身: ${msg.textContent}\n`;<br /> }<br /> });<br /> <br /> // 创建下载链接<br /> const blob = new Blob([historyText], { type: 'text/plain;charset=utf-8' });<br /> const url = URL.createObjectURL(blob);<br /> const a = document.createElement('a');<br /> a.href = url;<br /> a.download = `数字分身对话_${knowledgeBase}_${new Date().toISOString().slice(0, 19).replace(/:/g, '-')}.txt`;<br /> document.body.appendChild(a);<br /> a.click();<br /> document.body.removeChild(a);<br /> URL.revokeObjectURL(url);<br /> }<br /> <br /> // 事件监听器<br /> sendButton.addEventListener('click', sendMessage);<br /> saveButton.addEventListener('click', saveChatHistory);<br /> <br /> messageInput.addEventListener('keypress', function(e) {<br /> if (e.key === 'Enter' &amp;&amp; !e.shiftKey) {<br /> e.preventDefault();<br /> sendMessage();<br /> }<br /> });<br /> <br /> // 页面加载时初始化连接并获取欢迎信息<br /> initializeConnection();<br /> <br /> // 每30秒自动测试连接状态（不显示消息）<br /> const connectionInterval = setInterval(async () =&gt; {<br /> await testConnection();<br /> }, 30000);<br /> });<br /> &lt;/script&gt;<br /> &lt;/body&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=%E6%8B%9B%E7%94%9F&diff=3472 2026-01-06T10:25:25Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=招生说明<br /> |content=<br /> * 个人简历请发送至 zhaosheng@mobinets.org，随时接收简历，交流及录取过程在每年3月(考研)和7-9月(保研)。<br /> * 由于实验室日常教学科研工作较多，建议保研同学在7-9月邮件联系，考研同学在2-4月份联系，以免邮件被错过。<br /> &lt;!--* '''20250715更新'''：近期接收简历较多，如未及时收到回信，请联系其他老师。祝各位同学一切顺利！--&gt;<br /> }}<br /> &lt;!--<br /> &lt;div align=&quot;center&quot;&gt;<br /> &lt;br&gt;<br /> &lt;big&gt;''''''''另：复试程序保障了提前联系团队与复试能否通过完全没有关联，请各位报名同学认真准备学院复试。''''''''&lt;/big&gt;<br /> 参考：<br /> [http://yjsjy.uestc.edu.cn/gmis/jcsjgl/dsfc/index/#08 电子科大研招网导师列表], <br /> [http://www.scse.uestc.edu.cn/sz.jsp?urltype=tree.TreeTempUrl&amp;wbtreeid=1081 学院师资介绍]<br /> &lt;/div&gt;<br /> '''2022拔尖计划纳新在[[Resource:拔尖计划纳新|这里]]'''<br /> --&gt;<br /> ===='''申请链接'''====<br /> * [[Resource:拔尖计划纳新|'''拔尖计划纳新'''（面向本校本科生）]]<br /> * [[招生常见问答|'''必读信息''']]<br /> * [[招生申请流程|申请流程]]<br /> <br /> ===='''团队简介'''====<br /> 团队主要研究方向包含泛在边缘计算和智能物联网系统。近五年在中国计算机学会(CCF)认定的A类期刊和会议及中科院认定的一区期刊上发表30余篇学术论文。团队成员承担中国国家自然基金、欧盟FP7项目、英国皇家学会、国家重点研发计划等国家级、省部级科研项目，并与华为、中移动等工业界企业具有良好的科研合作。实验室具有良好的硬件条件、严谨的科研氛围、融洽的师生关系，希望招收有志于在智慧物联网、智慧城市、未来网络演进等前沿课题有所建树的研究生和博士生，一起努力，共创未来。<br /> <br /> &lt;div align=&quot;center&quot;&gt;<br /> [[File:Team25.png|700px|link=]]<br /> [[File:humao.png|700px|link=]]<br /> &lt;/div&gt;<br /> <br /> &lt;!--<br /> &lt;gallery mode=&quot;slideshow&quot;&gt;<br /> File:humao.png|700px<br /> File:alumni.png|700px<br /> File:frontimg.png|700px<br /> &lt;/gallery&gt;<br /> --&gt;<br /> <br /> &lt;!--<br /> [[File:alumni.png|700px|link=]]<br /> [[File:frontimg.png|700px|link=]]<br /> --&gt;<br /> <br /> ===='''培养方式'''====<br /> 团队以学术创新为宗旨，对博士生和硕士生规划了不同的培养路线，确保学生和团队共同进步。<br /> <br /> ===== &gt;'''博士生培养'''=====<br /> (直博、硕博连读)<br /> [[File:phd.jpg|center|800px|link=]]<br /> ===== &gt;'''硕士生培养'''=====<br /> (分为科研与工程两类、研一及研二可择优转为硕博连读)<br /> [[File:ms.jpg|center|800px|link=]]<br /> <br /> &lt;br&gt;<br /> &lt;br&gt;<br /> ===='''毕业生去向'''====<br /> {{Former_members}}<br /> &lt;!--<br /> This page was last edited on {{REVISIONYEAR}}-{{REVISIONMONTH}}-{{REVISIONDAY}}.<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Previous_Seminars&diff=3461 2025-12-09T07:33:00Z

<p>Zhiwei: </p> <hr /> <div>=== History ===<br /> {{Hist_seminar<br /> |confname =ToN'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/10843977<br /> |title= Spliceosome: On-Camera Video Thinning and Tuning for Timely and Accurate Analytics<br /> |speaker=Zhongwei Sun<br /> |date=2025-11-28<br /> }}<br /> {{Hist_seminar<br /> |confname =NSDI'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/10843977<br /> |title= Accelerating Design Space Exploration for LLM Training Systems with Multi-experiment Parallel Simulation<br /> |speaker=Qinyong<br /> |date=2025-11-28<br /> }}<br /> {{Hist_seminar<br /> |confname =ASAP'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/11113621<br /> |title= ReaLLM: A Trace-Driven Framework for Rapid Simulation of Large-Scale LLM Inference<br /> |speaker=JunZhe<br /> |date=2025-11-21<br /> }}{{Hist_seminar<br /> |abstract =With the proliferation of mobile devices, spatial crowdsourcing has emerged as a promising paradigm for facilitating location-based services, encompassing various applications across academia and industries. Recently, pioneering works have attempted to infer workers' mobility patterns from historical data to improve the quality of task assignment. However, these studies have overlooked or under-examined issues such as the dynamic mobility patterns of crowd workers, especially in the context of newcomers, the misalignment between the objectives of mobility prediction and task assignment, and the effective utilization of predicted mobility patterns. In this paper, we investigate a problem we term Task Assignment in Mobility Prediction-aware Spatial Crowdsourcing (TAMP). To address the TAMP problem, we first propose a task-adaptive meta-learning algorithm, which trains a set of specific meta-knowledge for workers' mobility prediction models through game theory-based learning task clustering and meta-training within each cluster. Then, we design a task assignment-oriented loss function and develop a task assignment algorithm that incorporates prediction performance, prioritizing assignments with higher confidence of completion. Extensive experiments on real-world datasets validate that our proposed methods can effectively improve the quality of task assignment.<br /> |confname =ICDE'25<br /> |link = https://ieeexplore.ieee.org/document/11113007<br /> |title= Effective Task Assignment in Mobility Prediction-Aware Spatial Crowdsourcing<br /> |speaker= Zhenguo<br /> |date=2025-11-21<br /> }}{{Hist_seminar<br /> |abstract = Entanglement distribution across remote distances is critical for many quantum applications. Currently, the de facto approach for remote entanglement distribution relies on optical fiber for on-the-ground entanglement distribution. However, the fiber-based approach is incapable of global-scale entanglement distribution due to intrinsic limitations. This paper investigates a new hybrid ground-satellite quantum network architecture (QuESat) for global-scale entanglement distribution, integrating an on-the-ground fiber network with a global-scale passive optical network built with low-Earth-orbit satellites. The satellite network provides dynamic construction of photon lightpaths based on near-vacuum beam guides constructed via adjustable arrays of lenses, forwarding photons from one ground station to another with very high efficiency over long distances compared to using fiber. To assess the feasibility and effectiveness of QuESat for global communication, we formulate lightpath provisioning and entanglement distribution problems, considering the orbital dynamics of satellites and the time-varying entanglement demands from ground users. A two-stage algorithm is developed to dynamically configure the beam guides and distribute entanglements, respectively. The algorithm combines randomized and deterministic rounding for lightpath provisioning to enable global connectivity, with optimal entanglement swapping for distributing entanglements to meet users' demands. By developing a ground-satellite quantum network simulator, QuESat achieves multi-fold improvements compared to repeater networks.<br /> |confname = INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/document/11044649<br /> |title= QuESat: Satellite-Assisted Quantum Internet for Global-Scale Entanglement Distribution<br /> |speaker= Yaliang<br /> |date=2025-11-07<br /> }}{{Hist_seminar<br /> |abstract =The global business of transnational enterprises demands geo-distributed databases, where the leader-follower-based consensus protocols are the key to guaranteeing consistency of replicas spread across regions. Compared with traditional databases running in a single data center, determining which node is the leader in consensus protocol has a greater per-formance impact in geo-distributed databases running across multiple data centers. However, the performance of legacy leader management is far from satisfactory due to the network and application dynamics (e.g., network delay, node popularity, operation read-write ratio). This paper proposes GeoLM toward performance-oriented leader management for geo-distributed consensus protocols. GeoLM captures the network and application dynamics and proactively conducts seamless leader handovers with bounded switching costs. Our geo-distributed experimental results show that GeoLM improves performance up to 49.75% over the baselines (e.g., Raft and Geo-Raft) and achieves considerably good performance compared to state-of-the-art consensus protocols (e.g., SwiftPaxos, CURP, and EPaxos).<br /> |confname = INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/document/11044598<br /> |title= GeoLM: Performance-oriented Leader Management for Geo-Distributed Consensus Protocol<br /> |speaker= Linqi Liu<br /> |date=2025-11-07<br /> }}{{Hist_seminar<br /> |abstract = Immersive telepresence has the potential to revolutionize remote communication by offering a highly interactive and engaging user experience. However, state-of-the-art exchanges large volumes of 3D content to achieve satisfactory visual quality, resulting in substantial Internet bandwidth consumption. To tackle this challenge, we introduce MagicStream, a first-of-its-kind semantic-driven immersive telepresence system that effectively extracts and delivers compact semantic details of captured 3D representation of users, instead of traditional bit-by-bit communication of raw content. To minimize bandwidth consumption while maintaining low end-to-end latency and high visual quality, MagicStream incorporates the following key innovations: (1) efficient extraction of user's skin/cloth color and motion semantics based on lighting characteristics and body keypoints, respectively; (2) novel, real-time human body reconstruction from motion semantics; and (3) on-the-fly neural rendering of users' immersive representation with color semantics. We implement a prototype of MagicStream and extensively evaluate its performance through both controlled experiments and user trials. Our results show that, compared to existing schemes, MagicStream can drastically reduce Internet bandwidth usage by up to 1195X while maintaining good visual quality.<br /> |confname = Sensys'24<br /> |link = https://dl.acm.org/doi/10.1145/3666025.3699344<br /> |title= MagicStream: Bandwidth-conserving Immersive Telepresence via Semantic Communication<br /> |speaker= Mengfan Wang<br /> |date=2025-10-31<br /> }}{{Hist_seminar<br /> |abstract =To fulfill computing demands of numerous Internet of Things (IoT) devices in infrastructure-free regions, low earth orbit (LEO) satellite edge computing has been proposed in recent years, to circumvent the latency arising from long backhaul and link congestion in traditional cloud computing mode. This article proposes a novel time-varying graph-based collaborative task offloading strategy for LEO satellite IoT to reduce task computing latency. To this end, a computing coordinate graph (CCG) is designed to characterize the time-varying topology and resource distribution of LEO satellite networks. When a task is offloaded to LEO satellite networks because local computing capability is unable to meet latency constraint, the position of the task access satellite in the CCG is determined first. Then, the expanded hop counts from all satellite nodes to the access satellite are calculated, which informs the partitioning of different node sets. Afterwards, considering both link and on-board computing resources, with the access satellite as the reference node, the minimum total task computing latency for each node set is obtained in an ascending order of the expanded hop counts. Finally, the minimum one among obtained latency values is the anticipated total task computing latency. Simulation results demonstrate the effectiveness of the proposed task offloading strategy in reducing task computing latency.<br /> |confname = Systems Joural<br /> |link = https://ieeexplore.ieee.org/document/11024019<br /> |title= Collaborative Task Offloading for LEO Satellite Internet of Things: A Novel Computing Coordinate Graph-Based Approach<br /> |speaker= Yifei Zhou<br /> |date=2025-10-31<br /> }}<br /> {{Hist_seminar<br /> |abstract = Unlike traditional data collection applications (e.g., environment monitoring) that are dominated by uplink transmissions, the newly emerging applications (e.g., device actuation, firmware update, packet reception acknowledgement) also pose ever-increasing demands on downlink transmission capabilities. However, current LoRaWAN falls short in supporting such applications primarily due to downlink-uplink asymmetry. While the uplink can concurrently receive multiple packets, downlink transmission is limited to a single logical channel at a time, which fundamentally hinders the deployment of downlink-hungry applications. To tackle this practical challenge, FDLoRa develops the first-of-its-kind in-band full-duplex LoRa gateway design with novel solutions to mitigate the impact of self-interference (i.e., strong downlink interference to ultra-weak uplink reception), which unleashes the full spectrum for in-band downlink transmissions without compromising the reception of weak uplink packets. Built upon the full-duplex gateways, FDLoRa introduces a new downlink framework to support concurrent downlink transmissions over multiple logical channels of available gateways. Evaluation results demonstrate that FDLoRa boosts downlink capacity by 5.7x compared to LoRaWAN on a three-gateway testbed and achieves 2.58x higher downlink concurrency per gateway than the state-of-the-art.<br /> |confname = Sensys'24<br /> |link = https://dl.acm.org/doi/10.1145/3666025.3699338<br /> |title= FDLoRa: Tackling Downlink-Uplink Asymmetry with Full-duplex LoRa Gateways<br /> |speaker= Kai Chen<br /> |date=2025-10-23<br /> }}{{Hist_seminar<br /> |abstract =Recent years have witnessed a widespread adoption of containers. While containers simplify and accelerate application development, existing container network technologies either incur significant overhead, which hurts performance for distributed applications, or lose flexibility or compatibility, which hinders the widespread deployment in production. We carefully analyze the kernel data path of an overlay network, quantifying the time consumed by each segment of the data path and identifying the extra overhead in an overlay network compared to bare metal. We observe that this extra overhead generates repetitive results among packets, which inspires us to introduce caches within an overlay network. We design and implement ONCache (Overlay Network Cache), a cache-based container overlay network, to eliminate the extra overhead while maintaining flexibility and compatibility. We implement ONCache using the extended Berkeley Packet Filter (eBPF) with only 524 lines of code, and integrate it as a plugin of Antrea. With ONCache, containers attain networking performance akin to that of bare metal. Compared to the standard overlay networks, ONCache improves throughput and request-response transaction rate by 12% and 36% for TCP (20% and 34% for UDP), respectively, while significantly reducing per-packet CPU overhead. Popular distributed applications also benefit from ONCache.<br /> |confname = NSDI'25 <br /> |link = https://www.usenix.org/conference/nsdi25/presentation/lin-shengkai<br /> |title= ONCache: A Cache-Based Low-Overhead Container Overlay Network<br /> |speaker= Daobing Zeng<br /> |date=2025-10-24<br /> }}<br /> {{Hist_seminar<br /> |abstract = We present HyperCam, an energy-efficient image classification pipeline that enables computer vision tasks onboard low-power IoT camera systems. HyperCam leverages hyperdimensional computing to perform training and inference efficiently on low-power microcontrollers. We implement a low-power wireless camera platform using off-the-shelf hardware and demonstrate that HyperCam can achieve an accuracy of 93.60%, 84.06%, 92.98%, and 72.79% for MNIST, Fashion-MNIST, Face Detection, and Face Identification tasks, respectively, while significantly outperforming other classifiers in resource efficiency. \revSpecifically, it delivers inference latency of 0.08-0.27s while using 42.91-63.00KB flash memory and 22.25KB RAM at peak. Among other machine learning classifiers such as SVM, xgBoost, MicroNets, MobileNetV3, and MCUNetV3, HyperCam is the only classifier that achieves competitive accuracy while maintaining competitive memory footprint and inference latency that meets the resource requirements of low-power camera systems.<br /> |confname = Arxiv<br /> |link = https://arxiv.org/html/2501.10547v1<br /> |title= HyperCam: Low-Power Onboard Computer Vision for IoT Cameras<br /> |speaker= Menghao Liu<br /> |date=2025-10-17<br /> }}{{Hist_seminar<br /> |abstract = We present NIER, a video conferencing system that can adaptively maintain a low bitrate (e.g., 10–100 Kbps) with reasonable visual quality while being robust to packet losses. We use key-point-based deep image animation (DIA) as a key building block and address a series of networking and system challenges to make NIER practical. Our evaluations show that NIER significantly outperforms the baseline solutions.<br /> |confname =SIGCOMM'25 (short paper)<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3718958.3750518<br /> |title= NIER: Practical Neural-enhanced Low-bitrate Video Conferencing<br /> |speaker=Xinyan Wang<br /> |date=2025-9-26<br /> }}{{Hist_seminar<br /> |abstract = Distributed Edge Computing (DEC) has emerged as a novel paradigm, owing to its superior performance in communication latency, parallel computing efficiency, and energy consumption. With the surge of tasks in generative artificial intelligence, DEC faces higher demands for parallel computing efficiency. Scheduling multiple tasks for simultaneous processing, rather than one-by-one handling, could enhance parallel efficiency. Multiple tasks have multi-dependencies, i.e., sequence dependency, attribute similarity, and attribute correlation. Utilizing the bidirectional edges of traditional graphs to represent multi-dependencies can lead to an explosion in quantity. A hypergraph, with its hyperedges capable of connecting any number of vertices, can significantly solve the above problem. However, the multi-dependencies are rarely studied in the current research, posing the challenges, including incapable representing and unable capturing of multi-dependency hypergraph. In this work, we introduce a Joint communication and computation scheduling for hypErgraph Tasks in DEC, namely HypeJet, To effectively represent multi-dependencies, we employ hypergraph construction to represent task attributes and utilize hypergraph partitioning to clarify and refine task attribute correlations, enhancing parallel efficiency. In response to the challenge of capturing multi-dependencies, we employ a scheduling mechanism with the hypergraph neural network that efficiently acquires higher-order attribute correlated information among convolution matrices, providing enriched contextual information on multi-dependencies that supports decision-making in scheduling tasks. The evaluations using real-world traces demonstrate an 18.07% improvement in parallel efficiency of task scheduling.<br /> |confname =INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/11044587<br /> |title= HyperJet: Joint Communication and Computation Scheduling for Hypergraph Tasks in Distributed Edge Computing<br /> |speaker= Yi Zhou<br /> |date=2025-9-26<br /> }}{{Hist_seminar<br /> |abstract = Localization of networked nodes is an essential problem in emerging applications, including first-responder navigation, automated manufacturing lines, vehicular and drone navigation, asset tracking, Internet of Things, and 5G communication networks. In this paper, we present Locate3D, a novel system for peer-to-peer node localization and orientation estimation in large networks. Unlike traditional range-only methods, Locate3D introduces angle-of-arrival (AoA) data as an added network topology constraint. The system solves three key challenges: it uses angles to reduce the number of measurements required by 4× and jointly uses range and angle data for location estimation. We develop a spanning-tree approach for fast location updates, and to ensure the output graphs are rigid and uniquely realizable, even in occluded or weakly connected areas. Locate3D cuts down latency by up to 75% without compromising accuracy, surpassing standard range-only solutions. It has a 0.86 meter median localization error for building-scale multi-floor networks (32 nodes, 0 anchors) and 12.09 meters for large-scale networks (100,000 nodes, 15 anchors).<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/garg<br /> |title= Large Network UWB Localization: Algorithms and Implementation<br /> |speaker=Bangguo<br /> |date=2025-9-26<br /> }}<br /> {{Hist_seminar<br /> |abstract = With cloud-side computing and rendering, mobile cloud gaming (MCG) is expected to deliver high-quality gaming experiences to budget mobile devices. However, our measurement on representative MCG platforms reveals that even under good network conditions, all platforms exhibit high interactive latency of 112–403 ms, from a user-input action to its display response, that critically affects users’ quality of experience. Moreover, jitters in network latency often lead to significant fluctuations in interactive latency. In this work, we collaborate with a commercial MCG platform to conduct the first in-depth analysis on the interactive latency of cloud gaming. We identify VSync, the synchronization primitive of Android graphics pipeline, to be a key contributor to the excessive interactive latency; as many as five VSync events are intricately invoked, which serialize the complex graphics processing logic on both the client and cloud sides. To address this, we design an end-to-end VSync regulator, dubbed LoopTailor, which minimizes VSync events by decoupling game rendering from the lengthy cloud-side graphics pipeline and coordinating cloud game rendering directly with the client. We implement LoopTailor on the collaborated platform and commodity Android devices, reducing the interactive latency (by ∼34%) to stably below 100 ms.<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/li-yang<br /> |title= Dissecting and Streamlining the Interactive Loop of Mobile Cloud Gaming<br /> |speaker= Li Chen<br /> |date=2025-9-9<br /> }}{{Hist_seminar<br /> |abstract = The local deployment of large language models (LLMs) on mobile devices has garnered increasing attention due to its advantages in enhancing user privacy and enabling offline operation. However, given the limited computational resources of a single mobile device, only small language models (SLMs) with restricted capabilities can currently be supported. In this paper, we explore the potential of leveraging the collective computing power of multiple mobile devices to collaboratively support more efficient local LLM inference. We evaluate the feasibility and efficiency of existing parallelism techniques under the constraints of mobile devices and wireless network, identifying that chunked pipeline parallelism holds promise for realizing this vision. Building on this insight, we propose FlexSpark, a novel solution designed to achieve efficient and robust multi-device collaborative inference. FlexSpark incorporates priority scheduling, ordered communication, and elastic compression to maximize wireless bandwidth utilization, and thus accelerates distributed inference. Preliminary experimental results demonstrate that FlexSpark achieves up to a 2 × speedup compared to state-of-the-art frameworks, significantly enhancing the practicality and scalability of LLM deployment on mobile devices.<br /> |confname =APNet'25<br /> |link = https://dl.acm.org/doi/10.1145/3735358.3735368<br /> |title= FlexSpark: Robust and Efficient Multi-Device Collaborative Inference over Wireless Network<br /> |speaker=Ruizhen<br /> |date=2025-9-19<br /> }}<br /> {{Hist_seminar<br /> |abstract = Reconfigurable Intelligent Surfaces (RIS) are a promising technology for creating smart radio environments by controlling wireless propagation. However, several factors hinder the integration of RIS technology into existing cellular networks, including the incompatibility of RIS control interfaces with 5G PHY/MAC procedures for synchronizing radio scheduling decisions and RIS operation, and the cost and energy limitations of passive RIS technology. This paper presents RISENSE, a system for practical RIS integration in cellular networks. First, we propose a novel, low-cost, and low-power RIS design capable of decoding control messages without complex baseband operations or additional RF chains, utilizing a power sensor and a network of microstrip lines and couplers. Second, we design an effective in-band wireless RIS control interface, compatible with 5G PHY/MAC procedures, that embeds amplitude-modulated (AM) RIS control commands directly into standard OFDM-modulated 5G data channels. Finally, we propose a low-overhead protocol that supports swift on-demand RIS re-con gurability, making it adaptable to varying channel conditions and user mobility, while minimizing the wastage of 5G OFDM symbols. Our experiments validate the design of RISENSE and our evaluation shows that our system can reconfigure a RIS at the same pace as users move, boosting 5G coverage where static or slow RIS controllers cannot.<br /> |confname = Mobisys'25<br /> |link = https://dspace.networks.imdea.org/handle/20.500.12761/1925<br /> |title= RISENSE: Long-Range In-Band Wireless Control of Passive Reconfigurable Intelligent Surfaces<br /> |speaker= Haifeng<br /> |date=2025-9-12<br /> }}<br /> {{Hist_seminar<br /> |abstract = Traditional 3D content representations include dense point clouds that consume large amounts of data and hence network bandwidth, while newer representations such as neural radiance fields suffer from poor frame rates due to their non-standard volumetric rendering pipeline. 3D Gaussian splats (3DGS) can be seen as a generalization of point clouds that meet the best of both worlds, with high visual quality and efficient rendering for real-time frame rates. However, delivering 3DGS scenes from a hosting server to client devices is still challenging due to high network data consumption (e.g., 1.5 GB for a single scene). The goal of this work is to create an efficient 3D content delivery framework that allows users to view high quality 3D scenes with 3DGS as the underlying data representation. The main contributions of the paper are: (1) Creating new layered 3DGS scenes for efficient delivery, (2) Scheduling algorithms to choose what splats to download at what time, and (3) Trace-driven experiments from users wearing virtual reality headsets to evaluate the visual quality and latency. Our system for Layered 3D Gaussian Splats delivery (L3GS) demonstrates high visual quality, achieving 16.9% higher average SSIM compared to baselines, and also works with other compressed 3DGS representations. The code is available at https://github.com/mavens-lab/layered_3d_gaussian_splats.<br /> |confname =Mobicom'25<br /> |link = https://arxiv.org/html/2504.05517v1<br /> |title= L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery<br /> |speaker=Jiyi<br /> |date=2025-9-12<br /> }}<br /> {{Hist_seminar<br /> |abstract = This year, we are embracing the exciting new trends in AIoT including MLsys, LLMs, embodied perception, volumetric videos, etc. Papers collected from top venues in 2025 will be discussed in-depth, and research problems and new ideas are to be discovered!<br /> |confname = Begin of new semester<br /> |link = https://mobinets.cn/site/Resource:Paper_Carnival_2025<br /> |title= Paper Carnival 2025<br /> |speaker=All<br /> |date=2025-08-27<br /> }}<br /> {{Hist_seminar<br /> |abstract = In the metaverse era, point cloud video (PCV) streaming on mobile XR devices is pivotal. While most current methods focus on PCV compression from traditional 3-DoF video services, emerging AI techniques extract vital semantic information, producing content resembling the original. However, these are early-stage and computationally intensive. To enhance the inference efficacy of AI-based approaches, accommodate dynamic environments, and facilitate applicability to metaverse XR devices, we present ISCom, an interest-aware semantic communication scheme for lightweight PCV streaming. ISCom is featured with a region-of-interest (ROI) selection module, a lightweight encoder-decoder training module, and a learning-based scheduler to achieve real-time PCV decoding and rendering on resource-constrained devices. ISCom&amp;#x2019;s dual-stage ROI selection provides significantly reduces data volume according to real-time interest. The lightweight PCV encoder-decoder training is tailored to resource-constrained devices and adapts to the heterogeneous computing capabilities of devices. Furthermore, We provide a deep reinforcement learning (DRL)-based scheduler to select optimal encoder-decoder model for various devices adaptivelly, considering the dynamic network environments and device computing capabilities. Our extensive experiments demonstrate that ISCom outperforms baselines on mobile devices, achieving a minimum rendering frame rate improvement of 10 FPS and up to 22 FPS. Furthermore, our method significantly reduces memory usage by 41.7&amp;#x0025; compared to the state-of-the-art AITransfer method. These results highlight the effectiveness of ISCom in enabling lightweight PCV streaming and its potential to improve immersive experiences for emerging metaverse application.<br /> |confname =JSAC'24<br /> |link = https://dl.acm.org/doi/10.1109/JSAC.2023.3345430<br /> |title= ISCom: Interest-Aware Semantic Communication Scheme for Point Cloud Video Streaming on Metaverse XR Devices<br /> |speaker=Jiyi<br /> |date=2025-06-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = Scientific Illustration Tutorial<br /> |confname = TUTORIAL<br /> |link = https://mobinets.cn/Resource:Seminar<br /> |title= Idea share<br /> |speaker=OldBee<br /> |date=2025-06-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = Deploying deep convolutional neural networks (CNNs) for edge-based video analytics poses significant challenges due to the intensive computing demands. Model partitioning has emerged as a promising solution by offloading segments of CNNs to multiple proximal edge devices for collaborative inference. However, this approach often incurs substantial cross-device transmission overhead, particularly in handling intermediate feature maps. To address these limitations, we propose ReDream (REsidual feature-DRivEn mixed spArse coding for Model partitioning), a novel edge-centric video analytics framework that jointly optimizes transmission efficiency and inference accuracy. ReDream introduces two key innovations: 1) It enhances the sparsity of intermediate features by replacing activation functions with ReLU in selected CNN layers and retraining, thereby increasing the proportion of zero-valued elements. 2) It leverages the heterogeneous distribution of feature data across layers by applying a mixed sparse coding scheme, i.e., selecting different compression methods adaptively to optimize model partitioning. These optimizations enable ReDream to support more efficient cross-device inference while maintaining high model accuracy, making it well-suited for real-time deployment in collaborative edge environments.<br /> |confname = IDEA<br /> |link = https://mns.uestc.cn/wiki/Research:InProgress/MixedSparseCoding<br /> |title= ReDream: Residual Feature-Driven Mixed Sparse Coding for Model Partitioning<br /> |speaker=Xianyang<br /> |date=2025-05-23<br /> }}<br /> {{Hist_seminar<br /> |abstract = While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adopting context-awareness i.e. narrowing down a classification task to the current deployment context consisting of only recent inference queries can substantially enhance performance in resource-constrained environments. We propose a new paradigm, CACTUS, for scalable and efficient context-aware classification where a micro-classifier recognizes a small set of classes relevant to the current context and, when context change happens (e.g., a new class comes into the scene), rapidly switches to another suitable micro-classifier. CACTUS features several innovations, including optimizing the training cost of context-aware classifiers, enabling on-the-fly context-aware switching between classifiers, and balancing context switching costs and performance gains via simple yet effective switching policies. We show that CACTUS achieves significant benefits in accuracy, latency, and compute budget across a range of datasets and IoT platforms.<br /> |confname = Mobisys'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3643832.3661888<br /> |title= CACTUS: Dynamically Switchable Context-aware micro-Classifiers for Efficient IoT Inference<br /> |speaker= Zhenhua<br /> |date=2025-04-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Nowadays, volumetric videos have emerged as an attractive multimedia application providing highly immersive watching experiences since viewers could adjust their viewports at 6 degrees-of-freedom. However, the point cloud frames composing the video are prohibitively large, and effective compression techniques should be developed. There are two classes of compression methods. One suggests exploiting the conventional video codecs (2D-based methods) and the other proposes to compress the points in 3D space directly (3D-based methods). Though the 3D-based methods feature fast coding speeds, their compression ratios are low since the failure of leveraging inter-frame redundancy. To resolve this problem, we design a patch-wise compression framework working in the 3D space. Specifically, we search rigid moves of patches via the iterative closest point algorithm and construct a common geometric structure, which is followed by color compensation. We implement our decoder on a GPU platform so that real-time decoding and rendering are realized. We compare our method with GROOT, the state-of-the-art 3D-based compression method, and it reduces the bitrate by up to 5.98×. Moreover, by trimming invisible content, our scheme achieves comparable bandwidth demand of V-PCC, the representative 2D-based method, in FoV-adaptive streaming.<br /> |confname = TC'24<br /> |link = https://ieeexplore.ieee.org/document/10360355<br /> |title= A GPU-Enabled Real-Time Framework for Compressing and Rendering Volumetric Videos<br /> |speaker=Mengfan<br /> |date=2025-04-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing their private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE does not consider the heterogeneity among different clients, an intrinsic problem in cross-silo FL, often resulting in undermined training efficiency with slow convergence and stragglers. In this work, we propose FedPHE, an efficiently packed homomorphically encrypted FL framework with secure weighted aggregation and client selection to tackle the heterogeneity problem. Specifically, using CKKS with sparsification, FedPHE can achieve efficient encrypted weighted aggregation by accounting for contributions of local updates to the global model. To mitigate the straggler effect, we devise a sketching-based client selection scheme to cherry-pick representative clients with heterogeneous models and computing capabilities. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients’ privacy, achieve a training speedup of 1.85 − 4.44×, cut the communication overhead by 1.24 − 22.62× , and reduce the straggler effect by up to 1.71 − 2.39×.<br /> |confname =INFOCOM24'<br /> |link = https://ieeexplore.ieee.org/abstract/document/10621440<br /> |title= Efficient and Straggler-Resistant Homomorphic Encryption for Heterogeneous Federated Learning<br /> |speaker=Dongting<br /> |date=2025-03-28<br /> }}{{Hist_seminar<br /> |abstract = Entanglement routing (ER) in quantum networks must guarantee entanglement fidelity, a property that is crucial for applications such as quantum key distribution, quantum computation, and quantum sensing. Conventional ER approaches assume that network links can only generate entanglements with a fixed fidelity, and then they rely on purification to improve endto-end fidelities. However, recent advances in entanglement generation technologies show that quantum links can be configured by choosing among different fidelity/entanglement-rate combinations (defined in this paper as link configurations), hence enabling a more flexible assignment of quantum-network resources for meeting specific application requirements. To exploit this opportunity, we introduce the problem of link configuration for fidelityconstrained routing and purification (LC-FCRP) in Quantum Networks. We first formulate a simplified FCRP version as a Mixed Integer Linear Programming (MILP) model, where the link fidelity can be adjusted within a finite set. Then, to explore the full space of possible link configurations, we propose a link configuration algorithm based on a novel shortest-pathbased fidelity determination (SPFD) algorithm w/o Bayesian Optimization, which can be applied on top of any existing ER algorithm. Numerical results demonstrate that link configuration improves the acceptance ratio of existing ER algorithms by 87%.<br /> |confname =INFOCOM25'<br /> |link = https://re.public.polimi.it/bitstream/11311/1281986/1/final_infocom25_link_configuration_for_entanglement_routing.pdf<br /> |title= Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks<br /> |speaker=Yaliang<br /> |date=2025-03-27<br /> }}<br /> {{Hist_seminar<br /> |abstract = Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. This typically involves extensive sampling at inference time guided by an external LLM verifier, resulting in a two-player system. Despite external guidance, the effectiveness of this system demonstrates the potential of a single LLM to tackle complex tasks. Thus, we pose a new research problem: Can we internalize the searching capabilities to fundamentally enhance the reasoning abilities of a single LLM? This work explores an orthogonal direction focusing on post-training LLMs for autoregressive searching (i.e., an extended reasoning process with self-reflection and self-exploration of new strategies). To achieve this, we propose the Chain-of-Action-Thought (COAT) reasoning and a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning. Our approach results in Satori, a 7B LLM trained on open-source models and data. Extensive empirical evaluations demonstrate that Satori achieves state-of-the-art performance on mathematical reasoning benchmarks while exhibits strong generalization to out-of-domain tasks. Code, data, and models will be fully open-sourced.<br /> |confname = Arxiv<br /> |link = https://arxiv.org/abs/2502.02508<br /> |title= Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search<br /> |speaker=Qinyong<br /> |date=2025-03-14<br /> }}{{Hist_seminar<br /> |abstract = Light bulbs have been recently explored to design Light Fidelity (LiFi) communication to battery-free tags, thus complementing Radiofrequency (RF) backscatter in the uplink. In this paper, we show that LiFi and RF backscatter are complementary and have unexplored interactions. We introduce PassiveLiFi, a battery-free system that uses LiFi to transmit RF backscatter at a meagre power budget. We address several challenges on the system design in the LiFi transmitter, the tag and the RF receiver. We design the first LiFi transmitter that implements a chirp spread spectrum (CSS) using the visible light spectrum. We use a small bank of solar cells for both communication and harvesting, and reconfigure them based on the amount of harvested energy and desired data rate. We further alleviate the low responsiveness of solar cells with a new low-power receiver design in the tag. We design and implement a novel technique for embedding multiple symbols in the RF backscatter based on delayed chirps. Experimental results with an RF carrier of 17dBm show that we can generate RF backscatter with a range of 92.1 meters/ μW consumed in the tag, which is almost double with respect to prior work.<br /> |confname =ToN'23<br /> |link = https://ieeexplore.ieee.org/document/10371205/<br /> |title= LiFi for Low-Power and Long-Range RF Backscatter<br /> |speaker=Mengyu<br /> |date=2025-03-14<br /> }}<br /> {{Hist_seminar<br /> |abstract = Video analytics is widespread in various applications serving our society. Recent advances of content enhancement in video analytics offer significant benefits for the bandwidth saving and accuracy improvement. However, existing content-enhanced video analytics systems are excessively computationally expensive and provide extremely low throughput. In this paper, we present region-based content enhancement, that enhances only the important regions in videos, to improve analytical accuracy. Our system, RegenHance, enables high-accuracy and high-throughput video analytics at the edge by 1) a macroblock-based region importance predictor that identifies the important regions fast and precisely, 2) a region-aware enhancer that stitches sparsely distributed regions into dense tensors and enhances them efficiently, and 3) a profile-based execution planer that allocates appropriate resources for enhancement and analytics components. We prototype RegenHance on five heterogeneous edge devices. Experiments on two analytical tasks reveal that region-based enhancement improves the overall accuracy of 10-19% and achieves 2-3x throughput compared to the state-of-the-art frame-based enhancement methods.<br /> |confname =NSDI'25<br /> |link = https://arxiv.org/pdf/2407.16990<br /> |title= Region-based Content Enhancement for Efficient Video Analytics at the Edge<br /> |speaker=Xinyan<br /> |date=2025-03-07<br /> }}{{Hist_seminar<br /> |abstract = Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at this https URL<br /> |confname =AAAI'22<br /> |link = https://arxiv.org/abs/2112.02466<br /> |title= Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer<br /> |speaker=Bairong<br /> |date=2025-03-07<br /> }}<br /> {{Hist_seminar<br /> |abstract = The emerging programmable networks sparked significant research on Intelligent Network Data Plane (INDP), which achieves learning-based traffic analysis at line-speed. Prior art in INDP focus on deploying tree/forest models on the data plane. We observe a fundamental limitation in tree-based INDP approaches: although it is possible to represent even larger tree/forest tables on the data plane, the flow features that are computable on the data plane are fundamentally limited by hardware constraints. In this paper, we present BoS to push the boundaries of INDP by enabling Neural Network (NN) driven traffic analysis at line-speed. Many types of NNs (such as Recurrent Neural Network (RNN), and transformers) that are designed to work with sequential data have advantages over tree-based models, because they can take raw network data as input without complex feature computations on the fly. However, the challenge is significant: the recurrent computation scheme used in RNN inference is fundamentally different from the match-action paradigm used on the network data plane. BoS addresses this challenge by (i) designing a novel data plane friendly RNN architecture that can execute unlimited RNN time steps with limited data plane stages, effectively achieving line-speed RNN inference; and (ii) complementing the on-switch RNN model with an off-switch transformer-based traffic analysis module to further boost the overall performance. We implement a prototype of BoS using a P4 programmable switch as our data plane, and extensively evaluate it over multiple traffic analysis tasks. The results show that BoS outperforms state-of-the-art in both analysis accuracy and scalability..<br /> |confname =NSDI'24<br /> |link = https://www.usenix.org/conference/nsdi24/presentation/yan<br /> |title= Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed<br /> |speaker=Youwei<br /> |date=2025-02-28<br /> }}<br /> {{Hist_seminar<br /> |abstract = Recent advances in quantum information science enabled the development of quantum communication network prototypes and created an opportunity to study full-stack quantum network architectures. This work develops SeQUeNCe, a comprehensive, customizable quantum network simulator. Our simulator consists of five modules: hardware models, entanglement management protocols, resource management, network management, and application. This framework is suitable for simulation of quantum network prototypes that capture the breadth of current and future hardware technologies and protocols. We implement a comprehensive suite of network protocols and demonstrate the use of SeQUeNCe by simulating a photonic quantum network with nine routers equipped with quantum memories. The simulation capabilities are illustrated in three use cases. We show the dependence of quantum network throughput on several key hardware parameters and study the impact of classical control message latency. We also investigate quantum memory usage efficiency in routers and demonstrate that redistributing memory according to anticipated load increases network capacity by 69.1% and throughput by 6.8%. We design SeQUeNCe to enable comparisons of alternative quantum network technologies, experiment planning, and validation and to aid with new protocol design. We are releasing SeQUeNCe as an open source tool and aim to generate community interest in extending it.<br /> |confname =IOPSCIENCE'21<br /> |link = https://iopscience.iop.org/article/10.1088/2058-9565/ac22f6/meta<br /> |title= SeQUeNCe: a customizable discrete-event simulator of quantum networks<br /> |speaker=Junzhe<br /> |date=2025-02-21<br /> }}{{Hist_seminar<br /> |abstract = This article proposes a remote environmental monitoring system based on low-power Internet of Things, which is applied in smart agriculture to achieve remote and real-time measurement of temperature, humidity, and light intensity parameters in the crop growth environment within the coverage range of the device The system adopts low-power Internet of Things technology, which has the characteristics of wide coverage, multiple connections, fast speed, low cost, low power consumption, and excellent architecture. The overall design of the system includes multiple environmental monitoring nodes, a LoRa gateway, and corresponding environmental monitoring upper computer software. In terms of system software, it involves programming of node MCU and client upper computer software. The key technology implementation includes the hardware design and implementation of low-power sensor nodes and the development of LoRa protocol. System testing and performance analysis show that the optimized LoRa protocol performs well in communication distance, power consumption, stability, and other aspects, laying the foundation for the efficient operation of the system. This study provides a powerful tool for sustainable resource management, which helps to promote agricultural modernization and rural revitalization.<br /> |confname =CISCE'24<br /> |link = https://ieeexplore.ieee.org/abstract/document/10653076<br /> |title= A Long Distance Environmental Monitoring System Based on Low Power IoT<br /> |speaker= Ayesha Rasool<br /> |date=2025-02-21<br /> }}<br /> {{Hist_seminar<br /> |abstract = Recently, smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore the potential of infrastructure-assisted autonomous driving, this paper presents the design and deployment of Soar, the first end-to-end SRI system specifically designed to support autonomous driving systems. Soar consists of both software and hardware components carefully designed to overcome various system and physical challenges. Soar can leverage the existing operational infrastructure like street lampposts for a lower barrier of adoption. Soar adopts a new communication architecture that comprises a bi-directional multi-hop I2I network and a downlink I2V broadcast service, which are designed based on off-the-shelf 802.11ac interfaces in an integrated manner. Soar also features a hierarchical DL task management framework to achieve desirable load balancing among nodes and enable them to collaborate efficiently to run multiple data-intensive autonomous driving applications. We deployed a total of 18 Soar nodes on existing lampposts on campus, which have been operational for over two years. Our real-world evaluation shows that Soar can support a diverse set of autonomous driving applications and achieve desirable real-time performance and high communication reliability. Our findings and experiences in this work offer key insights into the development and deployment of next-generation smart roadside infrastructure and autonomous driving systems.<br /> |confname =MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3649352<br /> |title= Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving<br /> |speaker=Jiahao<br /> |date=2025-01-10<br /> }}{{Hist_seminar<br /> |abstract = GPUs are increasingly utilized for running DNN tasks on emerging mobile edge devices. Beyond accelerating single task inference, their value is also particularly apparent in efficiently executing multiple DNN tasks, which often have strict latency requirements in applications. Preemption is the main technology to ensure multitasking timeliness, but mobile edges primarily offer two priorities for task queues, and existing methods thus achieve only coarse-grained preemption by categorizing DNNs into real-time and best-effort, permitting a real-time task to preempt best-effort ones. However, the efficacy diminishes significantly when other real-time tasks run concurrently, but this is already common in mobile edge applications. Due to different hardware characteristics, solutions from other platforms are unsuitable. For instance, GPUs on traditional mobile devices primarily assist CPU processing and lack special preemption support, mainly following FIFO in GPU scheduling. Clouds handle concurrent task execution, but focus on allocating one or more GPUs per complex model, whereas on mobile edges, DNNs mainly vie for one GPU. This paper introduces Pantheon, designed to offer fine-grained preemption, enabling real-time tasks to preempt each other and best-effort tasks. Our key observation is that the two-tier GPU stream priorities, while underexplored, are sufficient. Efficient preemption can be realized through software design by innovative scheduling and novel exploitation of the nested redundancy principle for DNN models. Evaluation on a diverse set of DNNs shows substantial improvements in deadline miss rate and accuracy of Pantheon over state-of-the-art methods.<br /> |confname =MobiSys'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3643832.3661878<br /> |title= Pantheon: Preemptible Multi-DNN Inference on Mobile Edge GPUs<br /> |speaker=Jiale<br /> |date=2025-01-10<br /> }}<br /> {{Hist_seminar<br /> |abstract = Volumetric videos offer a unique interactive experience and have the potential to enhance social virtual reality and telepresence. Streaming volumetric videos to multiple users remains a challenge due to its tremendous requirements of network and computation resources. In this paper, we develop MuV2, an edge-assisted multi-user mobile volumetric video streaming system to support important use cases such as tens of students simultaneously consuming volumetric content in a classroom. MuV2 achieves high scalability and good streaming quality through three orthogonal designs: hybridizing direct streaming of 3D volumetric content with remote rendering, dynamically sharing edge-transcoded views across users, and multiplexing encoding tasks of multiple transcoding sessions into a limited number of hardware encoders on the edge. MuV2 then integrates the three designs into a holistic optimization framework. We fully implement MuV2 and experimentally demonstrate that MuV2 can deliver high-quality volumetric videos to over 30 concurrent untethered mobile devices with a single WiFi access point and a commodity edge server.<br /> |confname =MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3649364<br /> |title= MuV2: Scaling up Multi-user Mobile Volumetric Video Streaming via Content Hybridization and Sharing<br /> |speaker=Jiyi<br /> |date=2025-01-03<br /> }}{{Hist_seminar<br /> |abstract = The advent of 5G promises high bandwidth with the introduction of mmWave technology recently, paving the way for throughput-sensitive applications. However, our measurements in commercial 5G networks show that frequent handovers in 5G, due to physical limitations of mmWave cells, introduce significant under-utilization of the available bandwidth. By analyzing 5G link-layer and TCP traces, we uncover that improper interactions between these two layers causes multiple inefficiencies during handovers. To mitigate these, we propose M2HO, a novel device-centric solution that can predict and recognize different stages of a handover and perform state-dependent mitigation to markedly improve throughput. M2HO is transparent to the firmware, base stations, servers, and applications. We implement M2HO and our extensive evaluations validate that it yields significant improvements in TCP throughput with frequent handovers.<br /> |confname =MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3690680<br /> |title= M2HO: Mitigating the Adverse Effects of 5G Handovers on TCP<br /> |speaker=Jiacheng<br /> |date=2025-01-03<br /> }}<br /> ====2024====<br /> {{Hist_seminar<br /> |abstract = Packet routing in virtual networks requires virtual-to-physical address translation. The address mappings are updated by a single party, i.e., the network administrator, but they are read by multiple devices across the network when routing tenant packets. Existing approaches face an inherent read-write performance tradeoff: they either store these mappings in dedicated gateways for fast updates at the cost of slower forwarding or replicate them at end-hosts and suffer from slow updates.SwitchV2P aims to escape this tradeoff by leveraging the network switches to transparently cache the address mappings while learning them from the traffic. SwitchV2P brings the mappings closer to the sender, thus reducing the first packet latency and translation overheads, while simultaneously enabling fast mapping updates, all without changing existing routing policies and deployed gateways. The topology-aware data-plane caching protocol allows the switches to transparently adapt to changing network conditions and varying in-switch memory capacity.Our evaluation shows the benefits of in-network address mapping, including an up to 7.8× and 4.3× reduction in FCT and first packet latency respectively, and a substantial reduction in translation gateway load. Additionally, SwitchV2P achieves up to a 1.9× reduction in bandwidth overheads and requires order-of-magnitude fewer gateways for equivalent performance.<br /> |confname =SIGCOMM'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3651890.3672213<br /> |title= In-Network Address Caching for Virtual Networks<br /> |speaker=Dongting<br /> |date=2024-12-06<br /> }}{{Hist_seminar<br /> |abstract = Visible light communication (VLC) has become an important complementary means to electromagnetic communications due to its freedom from interference. However, existing Internet-of-Things (IoT) VLC links can reach only &lt;10 meters, which has significantly limited the applications of VLC to the vast and diverse scenarios. In this paper, we propose ChirpVLC, a novel modulation method to prolong VLC distance from ≤10 meters to over 100 meters. The basic idea of ChirpVLC is to trade throughput for prolonged distance by exploiting Chirp Spread Spectrum (CSS) modulation. Specifically, 1) we modulate the luminous intensity as a sinusoidal waveform with a linearly varying frequency and design different spreading factors (SF) for different environmental conditions. 2) We design range adaptation scheme for luminance sensing range to help receivers achieve better signal-to-noise ratio (SNR). 3) ChirpVLC supports many-to-one and non-line-of-sight communications, breaking through the limitations of visible light communication. We implement ChirpVLC and conduct extensive real-world experiments. The results show that ChirpVLC can extend the transmission distance of 5W COTS LEDs to over 100 meters, and the distance/energy utility is increased by 532% compared to the existing work.<br /> |confname = IDEA<br /> |link = https://uestc.feishu.cn/file/Pbq3bWgKJoTQObx79f3cf6gungb<br /> |title= ChirpVLC：Extending The Distance of Low-cost Visible Light Communication with CSS Modulation<br /> |speaker=Mengyu<br /> |date=2024-12-06<br /> }}<br /> {{Hist_seminar<br /> |abstract = On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. However, the intensive training workload and limited onboard computing resources pose significant challenges to the availability and efficiency of model training. While existing works address these challenges through native resource management optimization, we instead leverage our observation that edge environments usually comprise a rich set of accompanying trusted edge devices with idle resources beyond a single terminal. We propose Asteroid, a distributed edge training system that breaks the resource walls across heterogeneous edge devices for efficient model training acceleration. Asteroid adopts a hybrid pipeline parallelism to orchestrate distributed training, along with a judicious parallelism planning for maximizing throughput under certain resource constraints. Furthermore, a fault-tolerant yet lightweight pipeline replay mechanism is developed to tame the device-level dynamics for training robustness and performance stability. We implement Asteroid on heterogeneous edge devices with both vision and language models, demonstrating up to 12.2× faster training than conventional parallelism methods and 2.1× faster than state-of-the-art hybrid parallelism methods through evaluations. Furthermore, Asteroid can recover training pipeline 14× faster than baseline methods while preserving comparable throughput despite unexpected device exiting and failure.<br /> |confname = MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3649363<br /> |title= Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices<br /> |speaker=Congrong<br /> |date=2024-11-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = The need for cooperation among intelligent edge devices has popularized cooperative multi-agent reinforcement learning (MARL) in multi-target coverage. However, many research efforts rely heavily on parameter sharing among homogeneous agents, which hampers coverage performance. The heterogeneity of computing and sensing capabilities, along with the time-varying dynamics of computing resources, pose significant challenges. To address these challenges, we propose a resource-sensitive multi-agent reinforcement learning framework based on heterogeneous edge devices (SmartHE). SmartHE decomposes the target coverage task into two hierarchical levels: 1) Executor-level task: A central coordinator assigns a subset of executors (i.e., cameras or agents) to execute action policies, aiming to minimize overall policy inference time and energy consumption by leveraging resource heterogeneity. 2) Target-level task: Each executor ignores irrelevant targets that fall outside the coverage radius of the executor based on the estimated target states and ignores redundant targets that could be more effectively covered by other executors based on the utility estimation. This enables each executor to focus on extracting features that optimize coverage. Through this dual-task framework, SmartHE efficiently improves the system performance.<br /> |confname = IDEA<br /> |link = https://mobinets.cn/site/Resource:Seminar<br /> |title= SmartHE: Resource-sensitive MARL framework based on heterogeneous edge devices<br /> |speaker=Xianyang<br /> |date=2024-11-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = Collaborative inference is the current state-of-the-art solution for mobile-server neural network inference offloading. However, we find that existing collaborative inference solutions only focus on partitioning the DNN computation, which is only a small part of achieving an efficient DNN offloading system. What ultimately determines the performance of DNN offloading is how the execution system utilizes the characteristics of the given DNN offloading task on the mobile, network, and server resources of the offloading environment. To this end, we design CoActo, a DNN execution system built from the ground up for mobile-server inference offloading. Our key design philosophy is Coactive Inference Offloading, which is a new, improved concept of DNN offloading that adds two properties, 1) fine-grained expression of DNNs and 2) concurrency of runtime resources, to existing collaborative inference. In CoActo, system components go beyond simple model splitting of existing approaches and operate more proactively to achieve the coactive execution of inference workloads. CoActo dynamically schedules concurrent interleaving of the mobile, server, and network operations to actively increase resource utilization, enabling lower end-to-end latency. We implement CoActo for various mobile devices and server environments and evaluate our system with distinct environment settings and DNN models. The experimental results show that our system achieves up to 2.1 times speed-up compared to the state-of-the-art collaborative inference solutions.<br /> |confname = Mobisys'24<br /> |link = https://dl.acm.org/doi/10.1145/3643832.3661885<br /> |title= CoActo: CoActive Neural Network Inference Offloading with Fine-grained and Concurrent Execution<br /> |speaker=Zhenhua<br /> |date=2024-11-22<br /> }}<br /> {{Hist_seminar<br /> |abstract = Caching is an indispensable technique for low-cost and fast data serving. The eviction algorithm, at the heart of a cache, has been primarily designed to maximize efficiency—reducing the cache miss ratio. Many eviction algorithms have been designed in the past decades. However, they all trade off throughput, simplicity, or both for higher efficiency. Such a compromise often hinders adoption in production systems.This work presents SIEVE, an algorithm that is simpler than LRU and provides better than state-of-the-art efficiency and scalability for web cache workloads. We implemented SIEVE in five production cache libraries, requiring fewer than 20 lines of code changes on average. Our evaluation on 1559 cache traces from 7 sources shows that SIEVE achieves up to 63.2% lower miss ratio than ARC. Moreover, SIEVE has a lower miss ratio than 9 state-of-the-art algorithms on more than 45% of the 1559 traces, while the next best algorithm only has a lower miss ratio on 15%. SIEVE's simplicity comes with superior scalability as cache hits require no locking. Our prototype achieves twice the throughput of an optimized 16-thread LRU implementation. SIEVE is more than an eviction algorithm; it can be used as a cache primitive to build advanced eviction algorithms just like FIFO and LRU.<br /> |confname =NSDI'24<br /> |link = https://www.usenix.org/conference/nsdi24/presentation/zhang-yazhuo<br /> |title= SIEVE is Simpler than LRU: an Efficient Turn-Key Eviction Algorithm for Web Caches<br /> |speaker=Haotian<br /> |date=2024-11-22<br /> }}<br /> {{Hist_seminar<br /> |abstract = In this paper, we revisit the problem of the current routing system in terms of prediction scalability and routing result optimality. Specifically, the current traffic prediction models are not suitable for large urban networks due to the incomplete information of traffic conditions. Besides, existing routing systems can only plan the routes based on the past traffic conditions and struggle to update the optimal route for vehicles in real-time. As a result, the actual route taken by vehicles is different from the ground-truth optimal path. Therefore, we propose a Just-In-Time Predictive Route Planning framework to tackle these two problems. Firstly, we propose a Travel Time Constrained Top- kn Shortest Path algorithm which pre-computes a set of candidate paths with several switch points. This empowers vehicles to continuously have the opportunity to switch to better paths taking into account real-time traffic condition changes. Moreover, we present a query-driven prediction paradigm with ellipse-based searching space estimation, along with an efficient multi-queries handling mechanism. This not only allows for targeted traffic prediction by prioritizing regions with valuable yet outdated traffic information, but also provides optimal results for multiple queries based on real-time traffic evolution. Evaluations on two real-life road networks demonstrate the effectiveness and efficiency of our framework and methods.<br /> |confname =ICDE'24<br /> |link = https://ieeexplore.ieee.org/document/10598147/authors#authors<br /> |title= A Just-In-Time Framework for Continuous Routing<br /> |speaker=Zhenguo<br /> |date=2024-11-8<br /> }}<br /> {{Hist_seminar<br /> |abstract = Many networking tasks now employ deep learning (DL) to solve complex prediction and optimization problems. However, current design philosophy of DL-based algorithms entails intensive engineering overhead due to the manual design of deep neural networks (DNNs) for different networking tasks. Besides, DNNs tend to achieve poor generalization performance on unseen data distributions/environments. Motivated by the recent success of large language models (LLMs), this work studies the LLM adaptation for networking to explore a more sustainable design philosophy. With the powerful pre-trained knowledge, the LLM is promising to serve as the foundation model to achieve &quot;one model for all tasks&quot; with even better performance and stronger generalization. In pursuit of this vision, we present NetLLM, the first framework that provides a coherent design to harness the powerful capabilities of LLMs with low efforts to solve networking problems. Specifically, NetLLM empowers the LLM to effectively process multimodal data in networking and efficiently generate task-specific answers. Besides, NetLLM drastically reduces the costs of fine-tuning the LLM to acquire domain knowledge for networking. Across three networking-related use cases - viewport prediction, adaptive bitrate streaming and cluster job scheduling, we showcase that the NetLLM-adapted LLM significantly outperforms state-of-the-art algorithms.<br /> |confname =SIGCOMM'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3651890.3672268<br /> |title= NetLLM: Adapting Large Language Models for Networking<br /> |speaker=Yinghao<br /> |date=2024-11-8<br /> }}<br /> {{Hist_seminar<br /> |abstract = Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing two dedicated schedules for placing communication tasks. The proposed schedules eliminate redundant computations and communications and enable overlaps between intra-node and inter-node communications, ultimately reducing the overall training time. As the two schedules are not mutually exclusive, we provide comprehensive theoretical analyses and derive an automatic and accurate solution to determine which schedule should be applied in different scenarios. Experimental results on an 8-GPU server and a 32-GPU cluster demonstrate that Parm outperforms the state-of-the-art MoE training system, DeepSpeed-MoE, achieving 1.13× to 5.77× speedup on 1296 manually configured MoE layers and approximately 3× improvement on two real-world MoE models based on BERT and GPT-2.<br /> |confname =INFOCOM'24<br /> |link = https://ieeexplore.ieee.org/abstract/document/10621327<br /> |title= Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules<br /> |speaker=Mengqi<br /> |date=2024-11-1<br /> }}<br /> {{Hist_seminar<br /> |abstract = HD map is a key enabling technology towards fully autonomous driving. We propose VI-Map, the first system that leverages roadside infrastructure to enhance real-time HD mapping for autonomous driving. The core concept of VI-Map is to exploit the unique cumulative observations made by roadside infrastructure to build and maintain an accurate and current HD map. This HD map is then fused with on-vehicle HD maps in real time, resulting in a more comprehensive and up-to-date HD map. By extracting concise bird-eye-view features from infrastructure observations and utilizing vectorized map representations, VI-Map incurs low compute and communication overhead. We conducted end-to-end evaluations of VI-Map on a real-world testbed and a simulator. Experiment results show that VI-Map can construct decentimeter-level (up to 0.3 m) HD maps and achieve real-time (up to a delay of 42 ms) map fusion between driving vehicles and roadside infrastructure. This represents a significant improvement of 2.8× and 3× in map accuracy and coverage compared to the state-of-the-art online HD mapping approaches. A video demo of VI-Map on our real-world testbed is available at https://youtu.be/p2RO65R5Ezg.<br /> |confname=Mobicom'23<br /> |link = https://dl.acm.org/doi/abs/10.1145/3570361.3613280<br /> |title= VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous Driving<br /> |speaker=Wangyang<br /> |date=2024-11-1<br /> }}<br /> {{Hist_seminar<br /> |abstract = Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.<br /> |confname = ICDM'23<br /> |link = https://ieeexplore.ieee.org/abstract/document/10415812<br /> |title= Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution<br /> |speaker=Shuhong<br /> |date=2024-10-25<br /> }}<br /> {{Hist_seminar<br /> |abstract = The proliferation of edge devices has pushed computing from the cloud to the data sources, and video analytics is among the most promising applications of edge computing. Running video analytics is compute- and latency-sensitive, as video frames are analyzed by complex deep neural networks (DNNs) which put severe pressure on resource-constrained edge devices. To resolve the tension between inference latency and resource cost, we present Polly, a cross-camera inference system that enables co-located cameras with different but overlapping fields of views (FoVs) to share inference results between one another, thus eliminating the redundant inference work for objects in the same physical area. Polly’s design solves two basic challenges of cross-camera inference: how to identify overlapping FoVs automatically, and how to share inference results accurately across cameras. Evaluation on NVIDIA Jetson Nano with a real-world traffic surveillance dataset shows that Polly reduces the inference latency by up to 71.4% while achieving almost the same detection accuracy with state-of-the-art systems.<br /> |confname= INFOCOM'23<br /> |link = https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10229045<br /> |title= Cross-Camera Inference on the Constrained Edge<br /> |speaker=Xinyan<br /> |date=2024-10-25<br /> }}<br /> {{Hist_seminar<br /> |abstract = Smart cameras with on-device deep learning inference capabilities are enabling distributed video analytics at the data source without sending raw video data over the often unreliable and congested wireless network. However, how to unleash the full potential of the computing power of the camera network requires careful coordination among the distributed cameras, catering to the uneven workload distribution and the heterogeneous computing capabilities. This paper presents CrossVision, a distributed framework for real-time video analytics, that retains all video data on cameras while achieving low inference delay and high inference accuracy. The key idea behind CrossVision is that there is a significant information redundancy in the video content captured by cameras with overlapped Field-of-Views (FoVs), which can be exploited to reduce inference workload as well as improve inference accuracy between correlated cameras. CrossVision consists of three main components to realize its function: a Region-of-Interest (RoI) Matcher that discovers video content correlation based on a segmented FoV transformation scheme; a Workload Balancer that implements a randomized workload balancing strategy based on a bulk-queuing analysis, taking into account the cameras’ predicted future workload arrivals; an Accuracy Guard that ensures that the inference accuracy is not sacrificed as redundant information is discarded. We evaluate CrossVision in a hardware-augmented simulator and on real-world cross-camera datasets, and the results show that CrossVision is able to significantly reduce inference delay while improving the inference accuracy compared to a variety of baseline approaches.<br /> |confname= TMC'24<br /> |link = https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10202594<br /> |title= CrossVision: Real-Time On-Camera Video Analysis via Common RoI Load Balancing<br /> |speaker=Xinyan<br /> |date=2024-10-25<br /> }}<br /> {{Hist_seminar<br /> |abstract = LoRa is a promising technology that offers ubiquitous low-power IoT connectivity. With the features of multi-channel communication, orthogonal transmission, and spectrum sharing, LoRaWAN is poised to connect millions of IoT devices across thousands of logical channels. However, current LoRa gateways utilize hardwired Rx chains that cover only a small fraction (&lt;1%) of the logical channels, limiting the potential for massive LoRa communications. This paper presents XGate, a novel gateway design that uses a single Rx chain to concurrently receive packets from all logical channels, fundamentally enabling scalable LoRa transmission and flexible network access. Unlike hardwired Rx chains in the current gateway design, XGate allocates resources including software-controlled Rx chains and demodulators based on the extracted meta information of incoming packets. XGate addresses a series of challenges to efficiently detect incoming packets without prior knowledge of their parameter configurations. Evaluations show that XGate boosts LoRa concurrent transmissions by 8.4× than state-of-the-art.<br /> |confname=Mobicom' 24<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3636534.3649375<br /> |title= Revolutionizing LoRa Gateway with XGate: Scalable Concurrent Transmission across Massive Logical Channels<br /> |speaker=Chenkai<br /> |date=2024-10-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Deep learning training (DLT), e.g., large language model (LLM) training, has become one of the most important services in multitenant cloud computing. By deeply studying in-production DLT jobs, we observed that communication contention among different DLT jobs seriously influences the overall GPU computation utilization, resulting in the low efficiency of the training cluster. In this paper, we present Crux, a communication scheduler that aims to maximize GPU computation utilization by mitigating the communication contention among DLT jobs. Maximizing GPU computation utilization for DLT, nevertheless, is NP-Complete; thus, we formulate and prove a novel theorem to approach this goal by GPU intensity-aware communication scheduling. Then, we propose an approach that prioritizes the DLT flows with high GPU computation intensity, reducing potential communication contention. Our 96-GPU testbed experiments show that Crux improves 8.3% to 14.8% GPU computation utilization. The large-scale production trace-based simulation further shows that Crux increases GPU computation utilization by up to 23% compared with alternatives including Sincronia, TACCL, and CASSINI.<br /> |confname=SIGCOMM' 24<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3651890.3672239<br /> |title= Crux: GPU-Efficient Communication Scheduling for Deep Learning Training<br /> |speaker=Youwei<br /> |date=2024-10-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge from foundation models to navigation tasks. In this work, we propose a Pixel-guided Navigation skill (PixNav), which bridges the gap between the foundation models and the embodied navigation task. It is straightforward for recent foundation models to indicate an object by pixels, and with pixels as the goal specification, our method becomes a versatile navigation policy towards all different kinds of objects. Besides, our PixNav is a pure RGB-based policy that can reduce the cost of homeassistance robots. Experiments demonstrate the robustness of the PixNav which achieves 80+% success rate in the local path-planning task. To perform long-horizon object navigation, we design an LLM-based planner to utilize the commonsense knowledge between objects and rooms to select the best waypoint. Evaluations across both photorealistic indoor simulators and real-world environments validate the effectiveness of our proposed navigation strategy.<br /> |confname=ICRA' 24<br /> |link = https://ieeexplore.ieee.org/document/10610499<br /> |title= Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill<br /> |speaker=Qinyong<br /> |date=2024-10-11<br /> }}<br /> {{Hist_seminar<br /> |abstract = Datacenter networks today provide best-effort delivery—messages may observe unpredictable queueing, delays, and drops due to switch buffer overflows within the network. Such weak guarantees reduce the set of assumptions that system designers can rely upon from the network, thus introducing inefficiency and complexity in host hardware and software. We present Harmony, a datacenter network architecture that provides powerful &quot;congestion-free&quot; message delivery guarantees—each message, once transmitted by the sender, observes bounded queueing at each switch in the network. Thus, network delays are bounded in failure-free scenarios, and congestion-related drops are completely eliminated. We establish, both theoretically and empirically, that Harmony provides such powerful guarantees with near-zero overheads compared to best-effort delivery networks: it incurs a tiny additive latency overhead that diminishes with message sizes, while achieving near-optimal network utilization.<br /> |confname=NSDI' 24<br /> |link = https://www.usenix.org/conference/nsdi24/presentation/agarwal-saksham<br /> |title= Harmony: A Congestion-free Datacenter Architecture<br /> |speaker=Junzhe<br /> |date=2024-10-11<br /> }}<br /> {{Hist_seminar<br /> |abstract = Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing video analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13× and 2.19× (4.86× and 1.60× compared to the state-of-the-art), while achieving comparable tracking quality.<br /> |confname=TMC' 24<br /> |link = https://ieeexplore.ieee.org/abstract/document/10682605<br /> |title= Argus: Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras<br /> |speaker=Bairong<br /> |date=2024-9-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = We present FarfetchFusion, a fully mobile live 3D telepresence system. Enabling mobile live telepresence is a challenging problem as it requires i) realistic reconstruction of the user and ii) high responsiveness for immersive experience. We first thoroughly analyze the live 3D telepresence pipeline and identify three critical challenges: i) 3D data streaming latency and compression complexity, ii) computational complexity of volumetric fusion-based 3D reconstruction, and iii) inconsistent reconstruction quality due to sparsity of mobile 3D sensors. To tackle the challenges, we propose a disentangled fusion approach, which separates invariant regions and dynamically changing regions with our low-complexity spatio-temporal alignment technique, topology anchoring. We then design and implement an end-to-end system, which achieves realistic reconstruction quality comparable to existing server-based solutions while meeting the real-time performance requirements (&lt;100 ms end-to-end latency, 30 fps throughput, &lt;16 ms motion-to-photon latency) solely relying on mobile computation capability.<br /> |confname=MobiCom' 23<br /> |link = https://dl.acm.org/doi/abs/10.1145/3570361.3592525<br /> |title= FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform<br /> |speaker=Mengfan<br /> |date=2024-9-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = Increasing bandwidth demands of mobile video streaming pose a challenge in optimizing the Quality of Experience (QoE) for better user engagement. Multipath transmission promises to extend network capacity by utilizing multiple wireless links simultaneously. Previous studies mainly tune the packet scheduler in multipath transmission, expecting higher QoE by accelerating transmission. However, since Adaptive BitRate (ABR) algorithms overlook the impact of multipath scheduling on throughput prediction, multipath adaptive streaming can even experience lower QoE than single-path. This paper proposes Chorus, a cross-layer framework that coordinates multipath scheduling with adaptive streaming to optimize QoE jointly. Chorus establishes two-way feedback control loops between the server and the client. Furthermore, Chorus introduces Coarse-grained Decisions, which assist appropriate bitrate selection by considering the scheduling decision in throughput prediction, and Finegrained Corrections, which meet the predicted throughput by QoE-oriented multipath scheduling. Extensive emulation and real-world mobile Internet evaluations show that Chorus outperforms the state-of-the-art MPQUIC scheduler, improving average QoE by 23.5% and 65.7%, respectively. <br /> |confname=MobiCom' 24<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3636534.3649359<br /> |title= Chorus: Coordinating Mobile Multipath Scheduling and Adaptive Video Streaming<br /> |speaker=Jiahao<br /> |date=2024-9-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = In Distributed Quantum Computing (DQC), quantum bits (qubits) used in a quantum circuit may be distributed on multiple Quantum Computers (QCs) connected by a Quantum Data Network (QDN). To perform a quantum gate operation involving two qubits on different QCs, we have to establish an Entanglement Connection (EC) between their host QCs. Existing EC establishment schemes result in a long EC establishment time, and low quantum resource utilization.In this paper, we propose an Asynchronous Entanglement Routing and Provisioning (AEPR) scheme to minimize the task completion time in DQC systems. AEPR has three distinct features: (i). Entanglement Paths (EPs) for a given SD pair are predetermined to eliminate the need for runtime calculation; (ii). Entanglement Links (ELs) are created proactively to reduce the time needed create EL on demand; and (iii). For a given EC request, quantum swapping along an EP is performed by a repeater whenever two adjacent ELs are created, so precious quantum resources at the repeater can be released immediately thereafter for other ELs and ECs. Extensive simulations show that AEPR can save up to 76.05% of the average task completion time in DQC systems compared with the state-of-the-art entanglement routing schemes designed to maximize QDN throughput. <br /> |confname=INFOCOM' 23<br /> |link = https://doi.org/10.1109/infocom53939.2023.10229101<br /> |title= Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing<br /> |speaker=Yaliang<br /> |date=2024-9-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = Recent advances in network and mobile computing. <br /> |confname=Talk<br /> |link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2024<br /> |title=[[Resource:Paper_Carnival_2024|Paper Carnival 2024]]<br /> |speaker=All<br /> |date=2024-9-5 ~ 2024-9-6<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10355583<br /> |title=Hi2LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost<br /> |speaker=Jiyi<br /> |date=2024-07-05}}<br /> {{Hist_seminar<br /> |confname=ICRA'23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10160341<br /> |title=D2CoPlan: A Differentiable Decentralized Planner for Multi-Robot Coverage<br /> |speaker=Xianyang<br /> |date=2024-07-05}}<br /> {{Hist_seminar<br /> |confname=TMC'24<br /> |link=https://ieeexplore.ieee.org/abstract/document/10440565<br /> |title=Joint Deployment of Truck-drone Systems for Camera-based Object Monitoring<br /> |speaker=Luwei<br /> |date=2024-06-28}}<br /> {{Hist_seminar<br /> |confname=NSDI'23<br /> |link=https://www.usenix.org/conference/nsdi23/presentation/li-zhuqi<br /> |title=Dashlet: Taming Swipe Uncertainty for Robust Short Video Streaming<br /> |speaker=Mengqi<br /> |date=2024-06-28}}<br /> {{Hist_seminar<br /> |confname=MobiCom'23<br /> |link=https://arxiv.org/pdf/2308.06053<br /> |title=Cost-effective On-device Continual Learning over Memory Hierarchy with Miro<br /> |speaker=Jiale<br /> |date=2024-06-14}}<br /> {{Hist_seminar<br /> |confname=SEC'23<br /> |link=https://www.cs.hunter.cuny.edu/~sdebroy/publication-files/SEC2023_CR.pdf<br /> |title=On Balancing Latency and Quality of Edge-Native Multi-View 3D Reconstruction<br /> |speaker=Yang Wang<br /> |date=2024-06-14}}<br /> {{Hist_seminar<br /> |confname=MobiSys'21<br /> |link=https://dl.acm.org/doi/10.1145/3458864.3466867<br /> |title=RayTrack: enabling interference-free outdoor mobile VLC with dynamic field-of-view<br /> |speaker=Mengyu<br /> |date=2024-06-07}}<br /> {{Hist_seminar<br /> |confname=MM'23<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3581783.3613907<br /> |title=Hermes: Leveraging Implicit Inter-Frame Correlation for Bandwidth-Efficient Mobile Volumetric Video Streaming<br /> |speaker=Mengfan<br /> |date=2024-06-07}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3603269.3604853<br /> |title=Masking Corruption Packet Losses in Datacenter Networks with Link-local Retransmission<br /> |speaker=Jiacheng<br /> |date=2024-05-31}}<br /> {{Hist_seminar<br /> |confname=FAST '23<br /> |link=https://www.usenix.org/system/files/fast23-li-pengfei.pdf<br /> |title=ROLEX: A Scalable RDMA-oriented Learned Key-Value Store for Disaggregated Memory Systems<br /> |speaker=Haotian<br /> |date=2024-05-31}}<br /> {{Hist_seminar<br /> |confname=ICRA 2023<br /> |link=https://ieeexplore.ieee.org/document/10161345<br /> |title=Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistants<br /> |speaker=Zhenhua<br /> |date=2024-05-24}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://xplorestaging.ieee.org/document/10229025<br /> |title=RecMon: A Deep Learning-based Data Recovery System for Network Monitoring<br /> |speaker=Zhenguo<br /> |date=2024-05-24}}<br /> {{Hist_seminar<br /> |confname=IPSN 2023<br /> |link=https://dl.acm.org/doi/10.1145/3583120.3586963<br /> |title=FLoRa: Energy-Efficient, Reliable, and Beamforming-Assisted Over-The-Air Firmware Update in LoRa Networks<br /> |speaker=Kai Chen<br /> |date=2024-05-10}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/abstract/document/10228941/<br /> |title=Prophet: An Efficient Feature Indexing Mechanism for Similarity Data Sharing at Network Edge<br /> |speaker=Rong Cong<br /> |date=2024-05-10}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM 2020<br /> |link=https://dl.acm.org/doi/10.1145/3387514.3405853<br /> |title=Concurrent Entanglement Routing for Quantum Networks: Model and Designs<br /> |speaker=Yaliang<br /> |date=2024-04-28}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2023<br /> |link=https://dl.acm.org/doi/10.1145/3570361.3592523<br /> |title=NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras<br /> |speaker=Jiyi<br /> |date=2024-04-12}}<br /> {{Hist_seminar<br /> |confname=Neurips 2017<br /> |link=https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf<br /> |title=Attention Is All You Need<br /> |speaker=Qinyong<br /> |date=2024-04-12}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/document/10229104<br /> |title=Achieving Resilient and Performance-Guaranteed Routing in Space-Terrestrial Integrated Networks<br /> |speaker=Luwei<br /> |date=2024-03-29}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/document/10229043<br /> |title=Communication-aware DNN pruning<br /> |speaker=Shuhong<br /> |date=2024-03-29}}<br /> {{Hist_seminar<br /> |confname=IROS 2021<br /> |link=https://ieeexplore.ieee.org/abstract/document/9636344<br /> |title=Scalable Reinforcement Learning Policies for Multi-Agent Control<br /> |speaker=Xianyang<br /> |date=2024-03-22}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/document/10228936/<br /> |title=Breaking the Throughput Limit of LED-Camera Communication via Superposed Polarization<br /> |speaker=Mengyu<br /> |date=2024-03-22}}<br /> {{Hist_seminar<br /> |confname=MobiHoc '23<br /> |link=https://dl.acm.org/doi/10.1145/3565287.3610254<br /> |title=SRLoRa: Neural-enhanced LoRa Weak Signal Decoding with Multi-gateway Super Resolution<br /> |speaker=Pengfei<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=TMC '23<br /> |link=https://ieeexplore.ieee.org/document/9839387<br /> |title=Integrated Sensing and Communication in UAV Swarms for Cooperative Multiple Targets Tracking<br /> |speaker=Kun Wang<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/10.1145/3570361.3592496<br /> |title=Towards Spatial Selection Transmission for Low-end IoT devices with SpotSound<br /> |speaker=Jiajun<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=NSDI '23<br /> |link=https://www.usenix.org/conference/nsdi23/presentation/padmanabhan<br /> |title=Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge<br /> |speaker=Mengqi<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/10.1145/3570361.3592514<br /> |title=Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios<br /> |speaker=Yang Wang<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10228884<br /> |title=DisProTrack: Distributed Provenance Tracking over Serverless Applications<br /> |speaker=Xinyu<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=MobiSys '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3581791.3596855<br /> |title=When VLC Meets Under-Screen Camera<br /> |speaker=Jiacheng<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3570361.3592530<br /> |title=MetaStream: Live Volumetric Content Capture, Creation, Delivery, and Rendering in Real Time<br /> |speaker=Jiale<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=ToSN '23<br /> |link=https://dl.acm.org/doi/10.1145/3571586<br /> |title=Decoding LoRa Collisions via Parallel Alignment<br /> |speaker=Kai Chen<br /> |date=2024-01-04}}<br /> {{Hist_seminar<br /> |confname=MASS '23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10298524<br /> |title=WiMix: A Lightweight Multimodal Human Activity Recognition System based on WiFi and Vision<br /> |speaker=Haotian<br /> |date=2024-01-04}}<br /> {{Hist_seminar<br /> |confname=TMC '23<br /> |link=https://ieeexplore.ieee.org/document/9888056<br /> |title=A Multicriteria-Based Forwarding Strategy for Interest Flooding Mitigation on Named Data Wireless Networking<br /> |speaker=Zhenghua<br /> |date=2024-01-04}}<br /> <br /> ====2023====<br /> {{Hist_seminar<br /> |confname=SenSys' 22<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568547<br /> |title=LLDPC: A Low-Density Parity-Check Coding Scheme for LoRa Networks<br /> |speaker=Wengliang<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=ToN' 22<br /> |link=https://ieeexplore.ieee.org/document/9690589/<br /> |title=Continuous Network Update With Consistency Guaranteed in Software-Defined Networks<br /> |speaker=Yaliang<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/document/10229105<br /> |title=OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos<br /> |speaker=Mengfan<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3603269.3604849<br /> |title=Network Load Balancing with In-network Reordering Support for RDMA<br /> |speaker=Jiyi<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=TMC '22<br /> |link=https://ieeexplore.ieee.org/abstract/document/10209220<br /> |title=F3VeTrac: Enabling Fine-grained, Fully-road-covered, and Fully-individual penetrative Vehicle Trajectory Recovery<br /> |speaker=Zhenguo<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3603269.3604819<br /> |title=ZGaming: Zero-Latency 3D Cloud Gaming by Image Prediction<br /> |speaker=Wenjie<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=NeurIPS '20<br /> |link=https://arxiv.org/abs/2010.13110<br /> |title=Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks<br /> |speaker=Jiahui<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3570361.3592522<br /> |title=CoreKube: An Efficient, Autoscaling and Resilient Mobile Core System<br /> |speaker=Qinyong<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=TMC '20<br /> |link=https://ieeexplore.ieee.org/document/8708935<br /> |title=SmartVLC: Co-Designing Smart Lighting and Communication for Visible Light Networks<br /> |speaker=Mengyu<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=TMC '23<br /> |link=https://ieeexplore.ieee.org/document/9566795<br /> |title=A Fast, Reliable, Opportunistic Broadcast Scheme With Mitigation of Internal Interference in VANETs<br /> |speaker=Luwei<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/document/10228990<br /> |title=ResMap: Exploiting Sparse Residual Feature Map for Accelerating Cross-Edge Video Analytics<br /> |speaker=Xianyang<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=NSDI '23<br /> |link=https://www.usenix.org/conference/nsdi23/presentation/yu<br /> |title=Following the Data, Not the Function: Rethinking Function Orchestration in Serverless Computing<br /> |speaker=Mengfan<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=ASPLOS '23<br /> |link=https://dl.acm.org/doi/10.1145/3582016.3582050<br /> |title=LEGO: Empowering Chip-Level Functionality Plug-and-Play for Next-Generation IoT Devices<br /> |speaker=Pengfei<br /> |date=2023-11-09}}<br /> {{Hist_seminar<br /> |confname=IoTJ '23<br /> |link=https://ieeexplore.ieee.org/document/9714482?denied=<br /> |title=Hierarchical Aerial Computing for Internet of Things via Cooperation of HAPs and UAVs<br /> |speaker=Kun Wang<br /> |date=2023-11-09}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10229089<br /> |title=Search in the Expanse: Towards Active and Global IPv6 Hitlists<br /> |speaker=Xinyu<br /> |date=2023-11-2}}<br /> {{Hist_seminar<br /> |confname=IPSN '23<br /> |link=https://dl.acm.org/doi/10.1145/3583120.3586969<br /> |title=Link Quality Modeling for LoRa Networks in Orchards<br /> |speaker=Jiacheng<br /> |date=2023-11-02}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/document/10228896<br /> |title=Rebuffering but not Suffering: Exploring Continuous-Time Quantitative QoE by User’s Exiting Behaviors<br /> |speaker=Jiajun<br /> |date=2023-11-02}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://yuanmu97.github.io/preprint/packetgame_sigcomm23.pdf<br /> |title=PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale<br /> |speaker=Shuhong<br /> |date=2023-11-02}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3570361.3613271<br /> |title=Robust Real-time Multi-vehicle Collaboration on Asynchronous Sensors<br /> |speaker=Yang Wang<br /> |date=2023-10-26}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3603269.3604816<br /> |title=Ditto: Efficient Serverless Analytics with Elastic Parallelism<br /> |speaker=Mengqi Ma<br /> |date=2023-10-26}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/10.1145/3603269.3604832<br /> |title=CellFusion: Multipath Vehicle-to-Cloud Video Streaming with Network Coding in the Wild<br /> |speaker=Rong Cong<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |confname=SigMetrics '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3579445<br /> |title=DaeMon: Architectural Support for Efficient Data Movement in Fully Disaggregated Systems<br /> |speaker=Jiyi<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |confname=SenSys '22<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568533<br /> |title=MaLoRaGW: Multi-User MIMO Transmission for LoRa<br /> |speaker=Kai Chen<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '22<br /> |link=https://dl.acm.org/doi/10.1145/3544216.3544244<br /> |title=Software-defined network assimilation: bridging the last mile towards centralized network configuration management with NAssim<br /> |speaker=Yaliang<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |abstract = Recent advances in network and mobile computing. <br /> |confname=Talk<br /> |link=[Resource:Paper Carnival 2023|Paper Carnival 2023<br /> |title=]<br /> |speaker=All<br /> |date=2023-9-20<br /> }}<br /> {{Hist_seminar<br /> |abstract=Realizing Digital Twins for Vehicular Networks: Towards Future Network Evolution<br /> |confname=Tech. Talk<br /> |link=#<br /> |title=Trustworthy AI<br /> |speaker=Prof. Zhibo Wang<br /> |date=2023-07-11}}<br /> {{Hist_seminar<br /> |abstract=Realizing Digital Twins for Vehicular Networks: Towards Future Network Evolution<br /> |confname=submission<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=XX Towards Future Network Evolution<br /> |speaker=Zhenguo<br /> |date=2023-06-08}}<br /> {{Hist_seminar<br /> |abstract=Realizing Digital Twins for Vehicular Networks: Towards Future Network Evolution<br /> |confname=Tech. Talk<br /> |link=#<br /> |title=Rechargeable network<br /> |speaker=Prof. Tang Liu<br /> |date=2023-06-15}}<br /> {{Hist_seminar<br /> |abstract = Gondola<br /> |confname=SEC 2023<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Gondola: A Comprehensive Simulator for OEC<br /> |speaker=Qinyong<br /> |date=2023-06-08}}<br /> {{Hist_seminar<br /> |abstract=CHL<br /> |confname=INFOCOM 2024<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=CHL<br /> |speaker=Wenliang<br /> |date=2023-06-01}}<br /> {{Hist_seminar<br /> |abstract = EdgeLight<br /> |confname=SEC 2023<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=EdgeLight<br /> |speaker=Xianyang<br /> |date=2023-06-01}}<br /> {{Hist_seminar<br /> |confname=Sensys 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568527<br /> |title=Enhancing Video Analytics Accuracy via Real-time Automated Camera Parameter Tuning<br /> |speaker=Silence<br /> |date=2023-05-25}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://arxiv.org/pdf/2301.06363<br /> |title=A2-UAV: Application-Aware Content and Network Optimization of Edge-Assisted UAV Systems<br /> |speaker=Jiahui<br /> |date=2023-05-25}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9519523<br /> |title=Quick and Reliable LoRa Physical-layer Data Aggregation through Multi-Packet Reception<br /> |speaker=Kaiwen<br /> |date=2023-05-11}}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3560517<br /> |title=MobiDepth: real-time depth estimation using on-device dual cameras<br /> |speaker=Wenjie<br /> |date=2023-05-11}}<br /> {{Hist_seminar<br /> |confname=SEC 2022<br /> |link=https://ieeexplore.ieee.org/abstract/document/9996714<br /> |title=ENTS: An Edge-native Task Scheduling System for Collaborative Edge Computing<br /> |speaker=Qinyong<br /> |date=2023-05-11}}<br /> {{Hist_seminar<br /> |confname=TMC 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9519523<br /> |title=An Efficient Cooperative Transmission Based Opportunistic Broadcast Scheme in VANETs<br /> |speaker=Luwei<br /> |date=2023-05-04}}<br /> {{Hist_seminar<br /> |confname=CVPR 2022<br /> |link=https://arxiv.org/pdf/2203.09249.pdf<br /> |title=Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning<br /> |speaker=Jiaqi<br /> |date=2023-05-04}}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8978742<br /> |title=Pushing the Data Rate of Practical VLC via Combinatorial Light Emission<br /> |speaker=Mengyu<br /> |date=2023-05-04}}<br /> {{Hist_seminar<br /> |confname=SenSys 2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3384419.3430898<br /> |title=Deep compressive offloading: speeding up neural network inference by trading edge computation for network latency<br /> |speaker=Crong<br /> |date=2023-04-27}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9796804<br /> |title=DBAC: Directory-Based Access Control for Geographically Distributed IoT Systems<br /> |speaker=Xinyu<br /> |date=2023-04-27}}<br /> {{Hist_seminar<br /> |confname=SenSys 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568501<br /> |title=Turbo: Opportunistic Enhancement for Edge Video Analytics<br /> |speaker=Jiajun<br /> |date=2023-04-27}}<br /> {{Hist_seminar<br /> |confname=IPSN 2023<br /> |link=https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/602741/ipsn23-22.pdf?sequence=1&amp;isAllowed=y<br /> |title=Hydra: Concurrent Coordination for Fault-tolerant Networking<br /> |date=2023-04-20<br /> |speaker=Pengfei}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3517021<br /> |title=Experience: practical indoor localization for malls<br /> |date=2023-04-20<br /> |speaker=Zhuoliu}}<br /> {{Hist_seminar<br /> |confname=IWQoS 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9796680<br /> |title=Geographic Low-Earth-Orbit Networking without QoS Bottlenecks from Infrastructure Mobility<br /> |date=2023-04-20<br /> |speaker=Kun}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://www.jianguoyun.com/p/DaSn-A0Q_LXjBxjS9f8EIAA<br /> |title=Push the Limit of LPWANs with Concurrent Transmissions<br /> |date=2023-04-06<br /> |speaker=Wenliang}}<br /> {{Hist_seminar<br /> |confname=TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9942345<br /> |title=MOTO: Mobility-Aware Online Task Offloading with Adaptive Load Balancing in Small-Cell MEC<br /> |date=2023-04-06<br /> |speaker=Xianyang}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9796680<br /> |title=MoDEMS: Optimizing Edge Computing Migrations For User Mobility<br /> |date=2023-04-06<br /> |speaker=Zhenguo}}<br /> {{Hist_seminar<br /> |confname=IEEE Photonics Journal 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10028767<br /> |title=Physical-Layer Network Coding Enhanced Visible Light Communications Using RGB LEDs <br /> |date=2023-03-23<br /> |speaker=Jiahui}}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3498361.3539765<br /> |title=Tutti: coupling 5G RAN and mobile edge computing for latency-critical video analytics<br /> |date=2023-03-23<br /> |speaker=Silience}}<br /> {{Hist_seminar<br /> |confname=ACM Computing Surveys 2005<br /> |link=https://dl.acm.org/doi/10.1145/1118890.1118892<br /> |title=When and How to Develop Domain-Specific Languages<br /> |date=2023-03-23<br /> |speaker=Shu}}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3560544<br /> |title=BSMA: Scalable LoRa networks using full duplex gateways <br /> |date=2023-02-13<br /> |speaker=Kaiwen}}<br /> {{Hist_seminar<br /> |confname=MobiSys 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3498361.3539765<br /> |title=Memory-efficient DNN Training on Mobile Devices<br /> |date=2023-02-13<br /> |speaker=Wenjie}}<br /> {{Hist_seminar<br /> |confname=SigMetrics 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3530892<br /> |title=WiseFuse: Workload Characterization and DAG Transformation for Serverless Workflows <br /> |date=2023-02-13<br /> |speaker=Qinyong}}<br /> {{Hist_seminar<br /> |confname=Sensys2022<br /> |link=https://www4.comp.polyu.edu.hk/~csyqzheng/papers/HyLink-SenSys22.pdf<br /> |title=HyLink: Towards High Throughput LPWANs with LoRa Compatible Communication<br /> |date=2023-02-13<br /> |speaker=Mengyu}}<br /> {{Hist_seminar<br /> |confname=TMC 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9451627<br /> |title=Multi-Task Allocation in Mobile Crowd SensingWith Mobility Prediction <br /> |date=2023-02-13<br /> |speaker=Zhenguo}}<br /> {{Hist_seminar<br /> |confname=TMC2022<br /> |link=https://ieeexplore.ieee.org/document/9410408/<br /> |title=FLORA: Fuzzy Based Load-Balanced Opportunistic Routing for Asynchronous Duty-Cycled WSNs<br /> |date=2023-02-06<br /> |speaker=Luwei}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2022<br /> |link=https://dl.acm.org/doi/abs/10.1145/3495243.3560551<br /> |title=Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI <br /> |date=2023-02-06<br /> |speaker=Crong}}<br /> {{Hist_seminar<br /> |confname=MobiSys 2022<br /> |link=https://dl.acm.org/doi/abs/10.1145/3498361.3538919<br /> |title=TinyNET: a lightweight, modular, and unified network architecture for the internet of things<br /> |date=2023-02-06<br /> |speaker=Xinyu}}<br /> <br /> ====2022====<br /> {{Hist_seminar<br /> |confname=Mobicom2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3567652<br /> |title=IoTree: a battery-free wearable system with biocompatible sensors for continuous tree health monitoring<br /> |date=2022-11-25<br /> |speaker=Pengfei}}<br /> {{Hist_seminar<br /> |confname=TMC2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9373980<br /> |title=An Online Framework for Joint Network Selection and Service Placement in Mobile Edge Computing<br /> |date=2022-11-25<br /> |speaker=Kun}}<br /> {{Hist_seminar<br /> |confname=Sensys 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3485730.3485938<br /> |title=RT-mDL: Supporting Real-Time Mixed Deep Learning Tasks on Edge Platforms<br /> |date=2022-11-25<br /> |speaker=Jiajun}}<br /> {{Hist_seminar<br /> |confname=ICNP2022<br /> |link=https://www.jianguoyun.com/p/DUT5aHYQ_LXjBxiBx-UEIAA<br /> |title=Ostinato: Combating LoRa Weak Links in Real Deployments<br /> |speaker=Wenliang<br /> |date=2022-11-08}}<br /> {{Hist_seminar<br /> |confname=TMC2022<br /> |link=https://eprints.gla.ac.uk/274277/1/274277.pdf<br /> |title=A Unified Framework for Joint Sensing and Communication in Resource Constrained Mobile Edge Networks<br /> |speaker=Xianyang<br /> |date=2022-11-08}}<br /> {{Hist_seminar<br /> |confname=CVPR 2022<br /> |link=https://openaccess.thecvf.com/content/CVPR2022/papers/Dong_Federated_Class-Incremental_Learning_CVPR_2022_paper.pdf<br /> |title=Federated Class-Incremental Learning<br /> |speaker=Jianqi<br /> |date=2022-11-08}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2022<br /> |link=https://dl.acm.org/doi/abs/10.1145/3495243.3560551<br /> |title=Real-time neural network inference on extremely weak devices: agile offloading with explainable AI<br /> |speaker=Crong<br /> |date=2022-11-01<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://ieeexplore.ieee.org/document/9796711<br /> |title=An RFID and Computer Vision Fusion System for Book Inventory using Mobile Robot<br /> |speaker=Zhuoliu<br /> |date=2022-11-01<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3447993.3448631<br /> |title=One Tag, Two Codes: Identifying Optical Barcodes with NFC<br /> |date=2022-10-25<br /> |speaker=Jiangshu}}<br /> {{Hist_seminar<br /> |confname=IoTJ 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9444334<br /> |title=Service Coverage for Satellite Edge Computing<br /> |date=2022-10-25<br /> |speaker=Qinyong}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://arxiv.org/pdf/2203.10470<br /> |title=EdgeMatrix: A Resources Redefined Edge-Cloud System for Prioritized Services<br /> |date=2022-10-25<br /> |speaker=Xinyu}}<br /> {{Hist_seminar<br /> |confname=ICNP 2022<br /> |link=https://www.jianguoyun.com/p/DXDTOyEQ_LXjBxiLjt8EIAA<br /> |title=CONST: Exploiting Spatial-Temporal Correlation for Multi-Gateway based Reliable LoRa Reception<br /> |speaker=Kaiwen<br /> |date=2022-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://arxiv.org/pdf/2206.07509.pdf<br /> |title=Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading<br /> |speaker=Wenjie<br /> |date=2022-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9151371<br /> |title=Imitation Learning Enabled Task Scheduling for Online Vehicular Edge Computing<br /> |speaker=Zhenguo<br /> |date=2022-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3241539.3241543<br /> |title=ChromaCode: A Fully Imperceptible Screen-Camera Communication System<br /> |date=2022-10-10<br /> |speaker=Mengyu}}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9673682<br /> |title=MVPose:Realtime Multi-Person Pose Estimation using Motion Vector on Mobile Devices<br /> |date=2022-10-10<br /> |speaker=Silence}}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9352566<br /> |title=Optimizing Energy Consumption of Mobile Games<br /> |date=2022-10-10<br /> |speaker=Luwei}}<br /> {{Hist_seminar<br /> |abstract = Recent advances in network and mobile computing. <br /> |confname=talk<br /> |link=[Resource:Paper Carnival 2022|Paper Carnival 2022<br /> |title=]<br /> |speaker=all<br /> |date=2022-9-27<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488756<br /> |title=Resource-Efficient Federated Learning with Hierarchical Aggregation in Edge Computing<br /> |speaker=Jianqi<br /> |date=2022-6-27<br /> }}<br /> {{Hist_seminar<br /> |confname= ICDCS 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9546452<br /> |title=Gillis: Serving Large Neural Networks in Serverless Functions with Automatic Model Partitioning<br /> |speaker=Kun Wang<br /> |date=2022-6-27<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://www.jianguoyun.com/p/DWeMmMMQrvr2CBivtsYEIAA<br /> |title=Multi-Agent Distributed Reinforcement Learningfor Making Decentralized Offloading Decisions<br /> |speaker=Wenjie<br /> |date=2022-6-20<br /> }}<br /> {{Hist_seminar<br /> |confname= Sensys 2021<br /> |link=https://dl.acm.org/doi/abs/10.1145/3485730.3485929<br /> |title=FedMask: Joint Computation and Communication-Efficient Personalized Federated Learning via Heterogeneous Masking<br /> |speaker=Xinyu<br /> |date=2022-6-13<br /> }}<br /> {{Hist_seminar<br /> |confname= Sensys 2021<br /> |link=https://cse.msu.edu/~caozc/papers/sensys21-li.pdf<br /> |title=NELoRa: Towards Ultra-low SNR LoRa Communication with Neural-enhanced Demodulation<br /> |speaker=Kaiwen<br /> |date=2022-6-6<br /> }}<br /> {{Hist_seminar<br /> |confname= SenSys 2021<br /> |link=https://www.egr.msu.edu/~mizhang/papers/2021_SenSys_Mercury.pdf<br /> |title=Mercury: Efficient On-Device Distributed DNN Training via Stochastic Importance Sampling<br /> |speaker=Jiajun<br /> |date=2022-5-30<br /> }}<br /> {{Hist_seminar<br /> |confname= ATC 2020<br /> |link=https://www.usenix.org/system/files/atc20-tsai.pdf<br /> |title=Disaggregating Persistent Memory and Controlling Them Remotely: An Exploration of Passive Disaggregated Key-Value Stores<br /> |speaker=Qinyong<br /> |date=2022-5-30<br /> }}<br /> {{Hist_seminar<br /> |confname= TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9184260<br /> |title= Measurement Errors in Range-Based Localization Algorithms for UAVs: Analysis and Experimentation<br /> |speaker=Luwei<br /> |date=2022-5-23<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488426<br /> |title=AMIS:EdgeComputingBasedAdaptiveMobileVideoStreaming<br /> |speaker=Silence<br /> |date=2022-5-23<br /> }}<br /> {{Hist_seminar<br /> |confname= SIGCOMM 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3452296.3472893<br /> |title= XLINK: QoE-driven multi-path QUIC transport in large-scale video services<br /> |speaker=Rong<br /> |date=2022-5-9<br /> }}<br /> {{Hist_seminar<br /> |confname= IoTJ 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9612588<br /> |title=Stepwise Refinement Provenance Scheme for Wireless Sensor Networks<br /> |speaker=Zhuoliu<br /> |date=2022-5-9<br /> }}<br /> {{Hist_seminar<br /> |confname= IPSN 2022<br /> |link=http://www.carloalbertoboano.com/documents/yang22emu.pdf<br /> |title= EMU: Increasing the Performance and Applicability of LoRa through Chirp Emulation, Snipping, and Multiplexing<br /> |speaker=Wenliang<br /> |date=2022-4-29<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2022<br /> |link=https://www.usenix.org/system/files/nsdi22-paper-chen_jun_lin.pdf<br /> |title=Starlight: Fast Container Provisioning on the Edge and over the WAN<br /> |speaker=Jiangshu<br /> |date=2022-4-29<br /> }}<br /> {{Hist_seminar<br /> |confname= AAAI 2022<br /> |link=https://www.aaai.org/AAAI22Papers/AAAI-6846.YueT.pdf<br /> |title= FedProto: Federated Prototype Learning across Heterogeneous Clients<br /> |speaker=Jianqi<br /> |date=2022-4-22<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2022<br /> |link=https://www.usenix.org/system/files/nsdi22-paper-xu_jingao.pdf<br /> |title=SwarmMap: Scaling Up Real-time Collaborative Visual SLAM at the Edge<br /> |speaker=Jianfei<br /> |date=2022-4-12<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2022<br /> |link=https://www.usenix.org/system/files/nsdi22-paper-li_chenning.pdf<br /> |title=CurvingLoRa to Boost LoRa Network Throughput via Concurrent Transmission<br /> |speaker=Xiong<br /> |date=2022-4-15<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://cse.msu.edu/~caozc/papers/infocom22-li.pdf<br /> |title=CurveALOHA: Non-linear Chirps Enabled High Throughput Random Channel Access for LoRa<br /> |speaker=Xiong<br /> |date=2022-4-15<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://arxiv.org/pdf/2112.11818v1.pdf<br /> |title=Decentralized Task Offloading in Edge Computing: A Multi-User Multi-Armed Bandit Approach<br /> |speaker=Wenjie<br /> |date=2022-4-8<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://www2.cs.sfu.ca/~jcliu/Papers/casva22.pdf<br /> |title=CASVA: Configuration-Adaptive Streaming for Live Video Analytics<br /> |speaker=Shiqi<br /> |date=2022-4-8<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://xiaolongbupt.github.io/homepage_files/%5BPaper%5DWiRa_INFOCOM2022.pdf<br /> |title=WiRa: Enabling Cross-Technology Communication from WiFi to LoRa with IEEE 802.11ax<br /> |speaker=Kaiwen<br /> |date=2022-3-12<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488843<br /> |title=EdgeDuet: Tiling Small Object Detection for Edge Assisted Autonomous Mobile Vision<br /> |speaker=Xianyang<br /> |date=2022-3-12<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488741<br /> |title=Edge-assisted Online On-device Object Detection for Real-time Video Analytics<br /> |speaker=Silence<br /> |date=2022-3-4<br /> }}<br /> ====2021====<br /> {{Hist_seminar<br /> |confname= MobiCom 2021<br /> |link=https://dl.acm.org/doi/abs/10.1145/3447993.3483274<br /> |title=Flexible high-resolution object detection on edge devices with tunable latency<br /> |speaker=Rong<br /> |date=2021-12-24<br /> }}<br /> {{Hist_seminar<br /> |confname= TPDS 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9497712<br /> |title=Energy-Efficient Offloading for DNN-Based Smart IoT Systems in Cloud-Edge Environments<br /> |speaker=Wenjie<br /> |date=2021-12-24<br /> }}<br /> {{Hist_seminar<br /> |confname= TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9119834<br /> |title=Objective-Variable Tour Planning for Mobile Data Collection in Partitioned Sensor Networks<br /> |speaker=Zhuoliu<br /> |date=2021-12-24<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom 2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3372224.3419193<br /> |title=Nephalai: towards LPWAN C-RAN with physical layer compression<br /> |speaker=Wenliang<br /> |date=2021-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom 2021<br /> |link= https://dl.acm.org/doi/10.1145/3447993.3483242<br /> |title=EMP: edge-assisted multi-vehicle perception<br /> |speaker=Jiangshu<br /> |date=2021-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21spring-xu.pdf<br /> |title=Move Fast and Meet Deadlines: Fine-grained Real-time Stream Processing with Cameo<br /> |speaker=Jianfei<br /> |date=2021-12-10<br /> }}<br /> {{Hist_seminar<br /> |confname= ICML 2021<br /> |link= https://arxiv.org/pdf/2105.10056.pdf<br /> |title=Data-Free Knowledge Distillation for Heterogeneous Federated Learning<br /> |speaker=Jianqi<br /> |date=2021-12-10<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname= TWC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=939476<br /> |title=OMUS: Efficient Opportunistic Routing in Multi-Modal Underwater Sensor Networks<br /> |speaker=Xianyang<br /> |date=2021-12-3<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom 2021<br /> |link= https://dl.acm.org/doi/pdf/10.1145/3447993.3483250<br /> |title=Combating link dynamics for reliable lora connection in urban settings<br /> |speaker=Wangxiong<br /> |date=2021-12-3<br /> }}<br /> {{Hist_seminar<br /> |confname= IMWUT 2021<br /> |link= https://dl.acm.org/doi/pdf/10.1145/3478117<br /> |title=A City-Wide Crowdsourcing Delivery System with Reinforcement Learning<br /> |speaker=Wenjie<br /> |date=2021-12-3<br /> }}<br /> {{Hist_seminar<br /> |confname= TWC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9505263<br /> |title=Mega Satellite Constellation System Optimization: From Network Control Structure Perspective<br /> |speaker=Shiqi<br /> |date=2021-11-19<br /> }}<br /> {{Hist_seminar<br /> |confname= TWC 2021<br /> |link= https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9357996<br /> |title=Distance-Aware Relay Selection in an Energy-Efficient Discovery Protocol for 5G D2D Communication<br /> |speaker=Luwei<br /> |date=2021-11-19<br /> }}<br /> {{Hist_seminar<br /> |confname= ToN <br /> |link=https://ieeexplore.ieee.org/document/9525630<br /> |title=Adaptive Configuration Selection and Bandwidth Allocation for Edge-Based Video Analytics<br /> |speaker=Rong<br /> |date=2021-11-12<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom'21<br /> |link= https://dl.acm.org/doi/abs/10.1145/3447993.3483268<br /> |title=PCube: scaling LoRa concurrent transmissions with reception diversities<br /> |speaker=Kaiwen<br /> |date=2021-11-12<br /> }}<br /> {{Hist_seminar<br /> |confname= IMWUT 2021<br /> |link= https://dl.acm.org/doi/pdf/10.1145/3478117<br /> |title=A City-Wide Crowdsourcing Delivery System with Reinforcement Learning<br /> |speaker=Wenjie<br /> |date=2021-11-12<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS 2021<br /> |link=https://ieeexplore.ieee.org/document/9546470/<br /> |title=Defuse: A Dependency-Guided Function Scheduler to Mitigate Cold Starts on FaaS Platforms<br /> |speaker=Linyuanqi Zhang<br /> |date=2021-11-05<br /> }}<br /> {{Hist_seminar<br /> |confname=ICLR 2021<br /> |link=https://paperswithcode.com/paper/fedmix-approximation-of-mixup-under-mean-1<br /> |title=FedMix: Approximation of Mixup under Mean Augmented Federated Learning<br /> |speaker=Jianqi Liu<br /> |date=2021-11-05<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488721<br /> |title=Enhanced Flooding-Based Routing Protocol for Swarm UAV Networks: Random Network Coding Meets Clustering<br /> |speaker=Luwei<br /> |date=2021-10-29<br /> }}<br /> {{Hist_seminar<br /> |confname=IEEE Communications Surveys &amp; Tutorials 2018<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8386758<br /> |title=Routing in Multi-Hop Cellular Device-to-Device(D2D) Networks: A Survey<br /> |speaker=Wenjie<br /> |date=2021-10-29<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21-landa.pdf<br /> |title=Staying Alive: Connection Path Reselection at the Edge<br /> |speaker=Zhuoliu<br /> |date=2021-10-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/document/9488714<br /> |title=PolarTracker: Attitude-aware Channel Access for Floating Low Power Wide Area Networks<br /> |speaker=Wenliang<br /> |date=2021-10-15<br /> }}<br /> {{Hist_seminar<br /> |confname=SIGCOMM 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3452296.3472897<br /> |title=Hoplite: efficient and fault-tolerant collective communication for task-based distributed systems<br /> |speaker=Xianyang<br /> |date=2021-10-08<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21-tollman.pdf<br /> |title=EPaxos Revisited<br /> |speaker=Jianfei<br /> |date=2021-10-08<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom 2021<br /> |link=https://dl.acm.org/doi/10.1145/3447993.3448630<br /> |title=A community-driven approach to democratize access to satellite ground stations<br /> |speaker=Rong Cong<br /> |date=2021-09-24<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21-huang.pdf<br /> |title=Toward Nearly-Zero-Error Sketching via Compressive Sensing<br /> |speaker=Xiong Wang<br /> |date=2021-09-24<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9055089<br /> |title=Real-Time Detection for Drowsy Driving via Acoustic Sensing on Smartphones<br /> |speaker=Shiqi Hu<br /> |date=2021-09-17<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiHoc2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3466772.3467054<br /> |title=DeepLoRa: Fingerprinting LoRa Devices at Scale Through Deep Learning and Data Augmentation<br /> |speaker=Wenliang Mao<br /> |date=2021-09-17<br /> }}<br /> {{Hist_seminar<br /> |confname=IoTJ2021<br /> |link=https://ieeexplore.ieee.org/abstract/document/9386238<br /> |title=D2D-Enabled Mobile-Edge Computation Offloading for Multiuser IoT Network<br /> |speaker=Wenjie Huang<br /> |date=2021-09-17<br /> }}<br /> {{Hist_seminar<br /> |confname=talk<br /> |link=https://mobinets.cn/site/Resource:Paper_Carnival_2021<br /> |title= Sharing the state-of-the-art research works <br /> |speaker=All<br /> |date=2021-09-03<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'2020<br /> |link=https://ieeexplore.ieee.org/abstract/document/9259397<br /> |title= SCLoRa: Leveraging Multi-Dimensionality in Decoding Collided LoRa Transmissions<br /> |speaker=Wenliang Mao<br /> |date=2021-06-21<br /> }}<br /> {{Hist_seminar<br /> |confname=HotNets'2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3422604.3425938<br /> |title= &quot;Internet from Space&quot; without Inter-satellite Links?<br /> |speaker=Jiangshu Liu<br /> |date=2021-06-21<br /> }}<br /> {{Hist_seminar<br /> |confname=HotNets'2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3422604.3425926<br /> |title= A Distributed and Hybrid Ground Station Network for Low Earth Orbit Satellites<br /> |speaker=Jiangshu Liu<br /> |date=2021-06-21<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title= Path Reconstruction in Wireless Network<br /> |speaker=Luwei Fu<br /> |date=2021-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'2021<br /> |link=https://www.jianguoyun.com/p/DfMXogcQ_LXjBxiz6PkD<br /> |title= Mobility- and Load-Adaptive Controller Placement and Assignment in LEO Satellite Networks<br /> |speaker=Linyuanqi Zhang<br /> |date=2021-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title= Data Storage Management at Edge <br /> |speaker=Rong CONG<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=CONEXT Workshop 2019<br /> |link=https://dl.acm.org/doi/10.1145/3359993.3366644<br /> |title=Edge Data Repositories - The design of a store-process-send system at the Edge<br /> |speaker=Rong CONG<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=HotEdge 2018<br /> |link=https://www.usenix.org/conference/hotedge18/presentation/psaras<br /> |title=Mobile Data Repositories at the Edge<br /> |speaker=Rong CONG<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2021<br /> |link=https://www.researchgate.net/publication/346643946_Store_Edge_Networked_Data_SEND_A_Data_and_Performance_Driven_Edge_Storage_Framework<br /> |title=Store Edge Networked Data(SEND): A Data and Performance Driven Edge Storage Framework<br /> |speaker=Jiangshu Liu<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'2020<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9200665<br /> |title=Partial Computation Offloading and Adaptive Task Scheduling for 5G-enabled Vehicular Networks<br /> |speaker=Wenjie Huang<br /> |date=2021-05-25<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Two problems about my work: data collection and mobile charging scheme<br /> |speaker=Jianfei Zhang<br /> |date=2021-05-25<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'2021<br /> |link=http://wrap.warwick.ac.uk/145720/1/WRAP-trust-trackers-computation-offloading-edge-based-IoT-networks-Bradbury-2020.pdf<br /> |title=Trust Trackers for Computation Offloading in Edge-Based IoT Networks<br /> |speaker=Chang Shu<br /> |date=2021-05-12<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'2021<br /> |link=https://cse.msu.edu/~caozc/papers/infocom21-liu.pdf<br /> |title=Jamming of LoRa PHY and Countermeasure<br /> |speaker=Xiong Wang<br /> |date=2021-05-12<br /> }}<br /> {{Hist_seminar<br /> |confname=SenSys'20<br /> |link=https://dl.acm.org/doi/10.1145/3384419.3430770<br /> |title=SLoRa:Towards Secure LoRa Communications with Fine-grained Physical Layer Features<br /> |speaker=Wenliang Mao<br /> |date=2021-04-20<br /> }}<br /> {{Hist_seminar<br /> |confname=SenSys'20<br /> |link=https://dl.acm.org/doi/10.1145/3384419.3430731<br /> |title=Combating interference for long range LoRa sensing<br /> |speaker=Weifeng Gao<br /> |date=2021-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=TechReport<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=MA Ced federated learning<br /> |speaker=Xiaosong Wang<br /> |date=2021-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=TVT'2020<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9238415<br /> |title= Energy-Efficient and Delay-Fair Mobile Computation Offloading <br /> |speaker=Wenjie Huang<br /> |date=2021-4-7<br /> }}<br /> {{Hist_seminar<br /> |confname=TVT'2020<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8840972<br /> |title= A Utility Model for Photo Selection in Mobile Crowdsensing<br /> |speaker=Changsheng Liu<br /> |date=2021-4-7<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8960404<br /> |title= An Application Placement Technique for Concurrent IoT Applications in Edge and Fog Computing Environments<br /> |speaker=Jiwei Mo<br /> |date=2021-3-30<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8945405<br /> |title= Multi-Task Allocation Under Time Constraints in Mobile Crowdsensing<br /> |speaker=Luwei Fu<br /> |date=2021-3-30<br /> }}<br /> <br /> ====2020====<br /> {{Hist_seminar<br /> |confname=TMC'20<br /> |link=https://ieeexplore.ieee.org/abstract/document/9078842/<br /> |title=A Fuzzy Logic-based On-demand Charging Algorithm for Wireless Rechargeable Sensor Networks with Multiple Chargers<br /> |speaker=Rong Cong<br /> |date=2020-11-19<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Two problems about my work: data collection and mobile charging scheme<br /> |speaker=Wenjie Huang<br /> |date=2020-11-19<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=<br /> |title=The path planning algorithm for multiple mobile edge servers in EdgeGO<br /> |speaker=Rong Cong<br /> |date=2020-11-18<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=Mobisys20<br /> |link=https://dl.acm.org/doi/10.1145/3386901.3388913<br /> |title=Combating packet collisions using non-stationary signal scaling in LPWANs<br /> |speaker=Wenliang Mao<br /> |date=2020-11-18<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=<br /> |title=Dependency-Aware and Latency-Optimal Service Cache in Edge networks<br /> |speaker=Jiwei Mo<br /> |date=2020-11-18<br /> }}<br /> {{Hist_seminar<br /> |confname=talk<br /> |link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2019<br /> |title=[[Resource:Paper_Carnival_2020|Paper Carnival 2020]]<br /> |speaker=ALL<br /> |date=2020-09-24,25,26<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://infocom2020.ieee-infocom.org/accepted-paper-list-main-conference<br /> |title=Optimizing Federated Learning on Non-IID Data with Reinforcement Learning<br /> |speaker=YuHong Jiang<br /> |date = 2020-5-16<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://arxiv.org/pdf/2002.11850<br /> |title=Joint Optimization of Signal Design and Resource Allocation in Wireless D2D Edge Computing<br /> |speaker=Shiqi Hu<br /> |date=2020-4-20<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://www4.comp.polyu.edu.hk/~csyqzheng/papers/LiteNap-INFOCOM20.pdf<br /> |title=LiteNap: Downclocking LoRa Reception<br /> |speaker=Wenliang Mao<br /> |date=2020-4-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://arxiv.org/abs/2002.02596<br /> |title=Delay-Optimal Distributed Edge Computing in Wireless Edge Networks<br /> |speaker=Chang Shu<br /> |date= 2020-3-30<br /> }}<br /> {{Hist_seminar<br /> |confname=IoTJ 2018<br /> |link=https://ieeexplore.ieee.org/document/8371243<br /> |title=Over-the-Air Computation for IoT Networks: Computing Multiple Functions With Antenna Arrays<br /> |speaker=Yuhong Jiang<br /> |date=2020-3-23<br /> }}<br /> {{Hist_seminar<br /> |confname=SIGCOMM'19<br /> |link=https://dl.acm.org/doi/abs/10.1145/3341302.3342081<br /> |title=RF-based Inertial Measurement<br /> |speaker=Weifeng Gao<br /> |date=2020-3-16<br /> }}<br /> ====2019====<br /> <br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/3i4wf2M7nD3nbkXbcbx1Do/5ZUGADKwrq6X0AzD4emr9c.pdf<br /> |title=FRAME: Fault Tolerant and Real-Time Messaging for Edge Computing<br /> |speaker=Xiaosong Wang<br /> |date=2019-12-25<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8737456<br /> |title=Intelligent Edge-Assisted Crowdcast with Deep Reinforcement Learning for Personalized QoE<br /> |speaker=Hengwei Deng<br /> |date=2019-12-25<br /> }}<br /> {{Hist_seminar<br /> |confname=ieee communications magazine'18<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8466366<br /> |title=Orchestration of Microservices for IoT Using Docker and Edge Computing<br /> |speaker=Changsheng Liu<br /> |date=2019-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname=Computer Science'13<br /> |link=https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf<br /> |title=Playing Atari with Deep Reinforcement Learning<br /> |speaker=Jie Zhang<br /> |date=2019-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'19<br /> |link=https://icnp19.cs.ucr.edu/proceedings/MainConference/FullPapers/icnp2019-final8.pdf<br /> |title=Exploiting Rateless Codes and Cross-Layer Optimization for Low-Power Wide-Area Networks<br /> |speaker=Silin Feng<br /> |date=2019-11-13<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/yzgM12TqeMYjWMqMhtP8N/7zRQAZeZ0fbS1oMqRXu5YR.pdf<br /> |title=DMRA: A Decentralized Resource Allocation Scheme for Multi-SP Mobile Edge Computing<br /> |speaker=Jiwei Mo<br /> |date=2019-11-13<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'19<br /> |link=http://www.winlab.rutgers.edu/~luyang/papers/mobicom19_augmented_reality.pdf<br /> |title=Edge Assisted Real-time Object Detection for MobileAugmented Reality<br /> |speaker=Yunpeng Han<br /> |date=2019-11-06<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI'20<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar#<br /> |title=Frequency Configuration for Low-Power Wide-Area Networks in a Heartbeat<br /> |speaker=Xiong Wang<br /> |date=2019-11-06<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiSys'16<br /> |link=https://www.microsoft.com/en-us/research/publication/mobility-modeling-prediction-bike-sharing-systems-2/<br /> |title=Mobility Modeling and Prediction in Bike-Sharing Systems<br /> |speaker=Anqi Yang<br /> |date=2019-10-30<br /> }}<br /> {{Hist_seminar<br /> |confname=Tech. Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar#<br /> |title=LoRa Localization<br /> |speaker=Xuan Yang<br /> |date=2019-10-30<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'19<br /> |link=https://people.cs.uchicago.edu/~junchenj/docs/E2E_Sigcomm19.pdf<br /> |title=E2E: Embracing User Heterogeneity to ImproveQuality of Experience on the Web<br /> |speaker=Jingwei Li<br /> |date=2019-10-23<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://www.cse.ust.hk/~weiwa/papers/cmfl-icdcs19.pdf<br /> |title=CMFL: Mitigating Communication Overhead for Federated Learning<br /> |speaker=Yuhong Jiang<br /> |date=2019-10-23<br /> }}<br /> {{Hist_seminar<br /> |confname=Tech.Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar#<br /> |title=Report on LoRa reliable protocols<br /> |speaker=Wenliang Mao<br /> |date=2019-10-16<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/4s7uYmRKCj0LsGXo56pEeY/6q2XcJvusaWopfasaMSRAA.pdf<br /> |title=Computation Offloading for Mobile-Edge Computing with Multi-user<br /> |speaker=Chang Shu<br /> |date=2019-10-16<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=Paper_Carnival_2019<br /> |link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2019<br /> |title= [[Resource:Paper_Carnival_2019|Paper Carnival 2019]]<br /> |speaker=ALL<br /> |date=2019-09-28,29,30<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://netarchlab.tsinghua.edu.cn/~junbi/INFOCOM2019-1.pdf<br /> |title=Octans: Optimal Placement of Service Function Chains in Many-Core Systems<br /> |speaker=Yuntong Zhang<br /> |date=2019-05-22<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=https://ieeexplore.ieee.org/abstract/document/8737660<br /> |title=Adaptive Interference-Aware VNF Placement for Service-Customized 5G Network Slices<br /> |speaker=Zhe Wang<br /> |date=2019-05-22<br /> }}<br /> {{Hist_seminar<br /> |confname=Tech. Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Recent progress and further trends on EdgeCloudSim<br /> |speaker=Yunpeng Han<br /> |date=2019-04-19<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'19<br /> |link=https://arxiv.org/pdf/1812.03103.pdf<br /> |title=mD-Track: Leveraging Multi-Dimensionality for Passive Indoor Wi-Fi Tracking<br /> |speaker=Xuan Yang<br /> |date=2019-04-19<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Correctness and Performance for Stateful Chained Network Functions<br /> |speaker=Yunpeng Han<br /> |date=2019-04-19<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Charging Oriented Sensor Placement and Flexible Scheduling in Rechargeable WSN<br /> |speaker=Wenjie Huang<br /> |date=2019-04-12<br /> }}<br /> {{Hist_seminar<br /> |confname=SIGCOMM'13<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Developing a Predictive Model of Quality of Experience for Internet Video<br /> |speaker=Yuhong Jiang<br /> |date=2019-04-12<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Brush like a Dentist: Accurate Monitoring of Toothbrushing via Wrist-Worn Gesture Sensing<br /> |speaker=Jingwei Li<br /> |date=2019-03-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Nomad: An Efficient Consensus Approach for Latency-Sensitive Edge-Cloud Applications<br /> |speaker=Anqi Yang<br /> |date=2019-03-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Winning at the Starting Line: Joint Network Selection and Service Placement for Mobile Edge Computing<br /> |speaker=Chang Shu<br /> |date=2019-03-22<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Interference Recycling: Exploiting Interfering Signals to Enhance Data Transmission<br /> |speaker=Wenliang Mao<br /> |date=2019-03-22<br /> }}<br /> {{Hist_seminar<br /> |confname=COMST'18<br /> |link=https://ieeexplore.ieee.org/document/8430735/<br /> |title=Small Cells in the Forthcoming 5G/IoT: Traffic Modeling and Deployment Overview<br /> |speaker=Anqi Yang<br /> |date=2019-01-04<br /> }}<br /> <br /> ====2018====<br /> {{Hist_seminar<br /> |confname=SIGCOMM'18<br /> |link=https://conferences.sigcomm.org/events/apnet2018/papers/elastic_sketch.pdf<br /> |title=Elastic Sketch: Adaptive and Fast Network-wide Measurements<br /> |speaker=Wenliang Mao<br /> |date=2018-12-21<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/document/7458131/<br /> |title=Performance analysis of mobile data offloading in heterogeneous networks<br /> |speaker=Yunpeng Han<br /> |date=2018-12-06<br /> }}<br /> {{Hist_seminar<br /> |confname=COMST'18<br /> |link=https://ieeexplore.ieee.org/document/8430735/<br /> |title=Small Cells in the Forthcoming 5G/IoT: Traffic Modelling and Deployment Overview<br /> |speaker=Anqi Yang<br /> |date=2018-12-06<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=http://ieeexplore.ieee.org/document/7272098/<br /> |title=A Reliability-Augmented Particle Filter for Magnetic Fingerprinting based Indoor Localization on Sma<br /> |speaker=Wenjie Huang<br /> |date=2018-11-30<br /> }}<br /> {{Hist_seminar<br /> |confname=ToN'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8519737<br /> |title=A Distributed Computation Offloading Strategy in Small-Cell Networks Integrated With Mobile Edge Computing<br /> |speaker=Yuhong Jiang<br /> |date=2018-11-23<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8526830<br /> |title=Networking Support For Physical-Layer Cross-Technology Communication<br /> |speaker=Jingwei Li<br /> |date=2018-11-23<br /> }}<br /> {{Hist_seminar<br /> |confname=IoT Journal'18<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8361406<br /> |title=Mobile-Edge Computation Offloading for Ultra-Dense IoT Networks<br /> |speaker=Chang Shu<br /> |date=2018-11-16<br /> }}<br /> {{Hist_seminar<br /> |confname=IPSN'17<br /> |link=http://mpc.ece.utexas.edu/media/uploads/publishing/blend_ipsn17.pdf<br /> |title=BLEnd: Practical Continuous Neighbor Discovery for Bluetooth Low Energy<br /> |speaker=Minghang Yang<br /> |date=2018-11-16<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=LoRa Applications (two papers)<br /> |speaker=Xinyuan Huang<br /> |date=2018-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/abstract/document/8476204<br /> |title=Static and Mobile Target k-Coverage in Wireless Rechargeable Sensor Networks<br /> |speaker=Shuowei Chen<br /> |date=2018-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=EWSN'17<br /> |link=https://dl.acm.org/citation.cfm?id=3108015<br /> |title=MOR: Multichannel Opportunistic Routing for Wireless Sensor Networks<br /> |speaker=Xuan Yang<br /> |date=2018-10-12<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/abstract/document/7874147<br /> |title= Hermes: Latency Optimal Task Assignment for Resource-constrained Mobile Computing<br /> |speaker=Yunpeng Han<br /> |date=2018-10-12<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://www.youtube.com/watch?v=e02p7813kN8<br /> |title=FoggyCache: Cross-Device Approximate Computation Reuse<br /> |speaker=Jingwei Li<br /> |date=2018-09-30<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8406950/<br /> |title=Knowledge-centric proactive edge caching over mobile content distribution network<br /> |speaker=Anqi Yang<br /> |date=2018-09-21<br /> }}<br /> {{Hist_seminar<br /> |confname=TWC'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8443421/<br /> |title=Enhancing Video Rate Adaptation with Mobile Edge Computing and Caching in Software-defined Mobile Ne<br /> |speaker=Yuhong Jiang<br /> |date=2018-09-21<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://netlab.dcs.gla.ac.uk/uploads/files/4239e2a52ef02c46fbdccb8ad0de1448.pdf<br /> |title=Dynamic,Latency-Optimal vNF Placement at the Network Edge<br /> |speaker=Latency-Optimal vNF Placement at the Network Edge<br /> |date=Chang Shu}}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/abstract/document/7572937/<br /> |title=Neighbor Discovery and Rendezvous Maintenance with Extended Quorum Systems for Mobile Applications<br /> |speaker=Minghang Yang<br /> |date=2018-09-14<br /> }}<br /> {{Hist_seminar<br /> |confname=Special Session<br /> |link=http://mobinets.org/seminar/carnival18mns/program.pdf<br /> |title=3-day discussion on recent papers in wireless,networking and mobile<br /> |speaker=networking and mobile&lt;/a&gt;<br /> |date=Chang Shu}}<br /> {{Hist_seminar<br /> |confname=IPSN'18<br /> |link=https://dl.acm.org/citation.cfm?id=3207955<br /> |title=Charm: Exploiting Geographical Diversity Through Coherent Combining in Low-Power Wide-Area Networks<br /> |speaker=Weifeng Gao<br /> |date=2018-06-15<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=http://grid.hust.edu.cn/fmliu/vnf-scaling-infocom1<br /> |title=Adaptive VNF Scaling and Flow Routing with Proactive Demand Prediction<br /> |speaker=Chang Shu<br /> |date=2018-06-15<br /> }}<br /> {{Hist_seminar<br /> |confname=ComMag'17<br /> |link=https://ieeexplore.ieee.org/document/8004165/<br /> |title=The Algorithmic Aspects of Network Slicing<br /> |speaker=Yunpeng Han<br /> |date=2018-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=IPSN'18<br /> |link=https://dl.acm.org/citation.cfm?id=3207954<br /> |title=Continuous Wireless Link Rates for Internet of Things<br /> |speaker=Luqi Yang<br /> |date=2018-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://www.researchgate.net/publication/325190993<br /> |title=TwinBee: Reliable Physical-Layer Cross-Technology Communication with Symbol-Level Coding<br /> |speaker=Xinyuan Huang<br /> |date=2018-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=Invited Tech.Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Report on recent research progress<br /> |speaker=Songfan Li<br /> |date=2018-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=Special Session<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Scheduling Algorithms for Resource-Constrained Systems<br /> |speaker=Prof. Dakai Zhu from UTSA<br /> |date=2018-05-28<br /> }}<br /> {{Hist_seminar<br /> |confname=CVPR'17<br /> |link=https://ieeexplore.ieee.org/document/8099631/<br /> |title=Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning<br /> |speaker=Hui Cao<br /> |date=2018-05-21<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=http://people.umass.edu/hcai/<br /> |title=Self-Adapting Quorum-Based Neighbor Discovery in Wireless Sensor Networks<br /> |speaker=Minghang Yang<br /> |date=2018-05-21<br /> }}<br /> {{Hist_seminar<br /> |confname=Special Session<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=From Location to Activity: Human-centric Sensing and Analytics<br /> |speaker=Prof. Tao Gu<br /> |date=2018-05-11<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=#<br /> |title=LipPass: Lip Reading-based User Authentication on Smartphones Leveraging Acoustic Signals<br /> |speaker=Shuowei Chen<br /> |date=2018-04-27<br /> }}<br /> {{Hist_seminar<br /> |confname=JSAC'17<br /> |link=https://ieeexplore.ieee.org/document/8058433<br /> |title=QoE-Aware and Reliable Traffic Steering for Service Function Chaining in Mobile Networks<br /> |speaker=Zhe Wang<br /> |date=2018-04-27<br /> }}<br /> {{Hist_seminar<br /> |confname=JSAC'17<br /> |link=http://rboutaba.cs.uwaterloo.ca/Papers/Journals/20<br /> |title=Distributed Service Function Chaining<br /> |speaker=Yuntong Zhang<br /> |date=2018-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://arxiv.org/pdf/1801.05868<br /> |title=Joint Service Caching and Task Offloading for Mobile Edge Computing in Dense Networks<br /> |speaker=Zi Wang<br /> |date=2018-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://arxiv.org/pdf/1712.06056.pdf<br /> |title=One-Hop Out-of-Band Control Planes for Low-Power Multi-Hop Wireless Networks<br /> |speaker=Chang Shu<br /> |date=2018-03-16<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'16<br /> |link=https://pdfs.semanticscholar.org/8e22/6c40a8c056dc<br /> |title=OpenBox: A Software-De?ned Framework for Developing,Deploying,and Managing Network Functions<br /> |speaker=Deploying<br /> |date=and Managing Network Functions&lt;/a&gt;}}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=https://pdfs.semanticscholar.org/fa3b/9634b6057b3f<br /> |title=Empowering Low-Power Wide Area Networks in Urban Settings<br /> |speaker=Weifeng Gao<br /> |date=2018-02-02<br /> }}<br /> {{Hist_seminar<br /> |confname=ComMag16<br /> |link=http://ieeexplore.ieee.org/abstract/document/81988<br /> |title=Hypergraph Theory: Applications in 5G Heterogeneous Ultra-Dense Networks<br /> |speaker=Yunpeng Han<br /> |date=2018-01-26<br /> }}<br /> {{Hist_seminar<br /> |confname=TCST'17<br /> |link=http://ieeexplore.ieee.org/abstract/document/82372<br /> |title=Optimal UAV Route Planning for Coverage Search of Stationary Target in River<br /> |speaker=Hui Cao<br /> |date=2018-01-26<br /> }}<br /> <br /> ====2017====<br /> <br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://www.ntu.edu.sg/home/junluo/documents/Refle<br /> |title=ReflexCode: Coding with Superposed Reflection Light for LED-Camera Communication<br /> |speaker=Xinyuan Huang<br /> |date=2017-12-08<br /> }}<br /> {{Hist_seminar<br /> |confname=Proc. IEEE 2016<br /> |link=http://ieeexplore.ieee.org/document/7423655/<br /> |title=Using Smart Edge IoT Devices for Safer,Rapid Response With Industry IoT Control Operations<br /> |speaker=Rapid Response With Industry IoT Control Operations&lt;/a&gt;<br /> |date=Minghang Yang}}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://ieeexplore.ieee.org/document/8057039/<br /> |title=Approximation Algorithms for The NFV Service Distribution Problem<br /> |speaker=Yuntong Zhang<br /> |date=2017-11-24<br /> }}<br /> {{Hist_seminar<br /> |confname=CCS'17<br /> |link=https://endchan.xyz/.media/50cf379143925a3926298f8<br /> |title=DolphinAtack: Inaudible Voice Commands<br /> |speaker=Zifei Zhao<br /> |date=2017-11-24<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI'17<br /> |link=https://www.usenix.org/conference/nsdi17/technical<br /> |title=Improving User Perceived Page Load Times Using Gaze<br /> |speaker=Yaoyao Pang<br /> |date=2017-11-17<br /> }}<br /> {{Hist_seminar<br /> |confname=CoNEXT'16<br /> |link=https://dl.acm.org/citation.cfm?id=2999602<br /> |title=Flurries: Countless Fine-Grained NFs for Flexible Per-Flow Customization<br /> |speaker=Zhe Wang<br /> |date=2017-11-17<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://dl.acm.org/citation.cfm?id=3117843<br /> |title=PassiveVLC: Enabling Practical Visible Light Backscatter Communication for Battery-free IoT Applicat<br /> |speaker=Weifeng Gao<br /> |date=2017-11-10<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://ieeexplore.ieee.org/document/8057229/<br /> |title=Service Chain Embedding with Maximum Flow in Software-defined Network and Application to The Next-Ge<br /> |speaker=Chang Shu<br /> |date=2017-11-10<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumbe<br /> |title=BAC: Bandwidth-Aware Compression for EfficientLive Migration of Virtual Machines<br /> |speaker=Yunpeng Han<br /> |date=2017-11-03<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://dl.acm.org/ft_gateway.cfm?id=3117816&amp;ftid=<br /> |title=WEBee: Physical-Layer Cross-Technology Communication via Emulation<br /> |speaker=Shuowei Chen<br /> |date=2017-11-03<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=http://conferences.sigcomm.org/sigcomm/2017/files/<br /> |title=NFVnice: Dynamic Backpressure and Scheduling for NFV Service Chains<br /> |speaker=Hui Cao<br /> |date=2017-10-27<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://kabru.eecs.umich.edu/wordpress/wp-content/<br /> |title=Continuous Authentication for Voice Assistants<br /> |speaker=Heng Yuan<br /> |date=2017-10-27<br /> }}<br /> {{Hist_seminar<br /> |confname=TWC'17<br /> |link=http://ieeexplore.ieee.org/document/7929399/<br /> |title=Computation Offloading and Resource Allocation in Wireless Cellular Networks With Mobile Edge Computing<br /> |speaker=Xinyuan Huang<br /> |date=2017-10-20<br /> }}<br /> {{Hist_seminar<br /> |confname=ToN'17<br /> |link=http://ieeexplore.ieee.org/document/7784410/<br /> |title=Chase: Taming concurrent broadcast for flooding in asynchronous duty cycle networks<br /> |speaker=Minghang Yang<br /> |date=2017-10-20<br /> }}<br /> {{Hist_seminar<br /> |confname=TOSN'17<br /> |link=http://www.comp.nus.edu.sg/~mobashir/Resources/Pap<br /> |title=Improving Performance of Synchronous Transmission-Based Protocols Using Capture Effect over Multicha<br /> |speaker=Luqi Yang<br /> |date=2017-10-13<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=http://conferences.sigcomm.org/sigcomm/2017/files/<br /> |title=Dynamic Service Chaining with Dysco<br /> |speaker=Chang Shu<br /> |date=2017-10-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://personal.stevens.edu/~ychen6/papers/ER%20Ea<br /> |title=ER: Early Recognition of Inattentive Driving Leveraging Audio Devices on Smartphones<br /> |speaker=Zifei Zhao<br /> |date=2017-09-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=https://thawproject.files.wordpress.com/2017/04/li<br /> |title=LightTouch: Securely Connecting Wearables to Ambient Displays with User Intent<br /> |speaker=Yaoyao Pang<br /> |date=2017-09-22<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=https://users.cs.fiu.edu/~pand/publications/17info<br /> |title=Traffic Aware Placement of Interdependent NFV Middleboxes<br /> |speaker=Zhe Wang<br /> |date=2017-09-22<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=https://people.cs.clemson.edu/~hongxih/papers/SIGC<br /> |title=NFP: Enabling Network Function Parallelism in NFV<br /> |speaker=Yuntong Zhang<br /> |date=2017-09-22<br /> }}<br /> {{Hist_seminar<br /> |confname=NFV-SDN'16<br /> |link=https://www.net.t-labs.tu-berlin.de/~stefan/o4sdi1<br /> |title=Efficient service Graph Embedding: A Practical Approach<br /> |speaker=Chang Shu<br /> |date=2017-09-11<br /> }}<br /> {{Hist_seminar<br /> |confname=SenSys'17<br /> |link=http://www.simonduquennoy.net<br /> |title=Network-wide Consensus Utilizing the Capture Effect in Low-power Wireless Networks<br /> |speaker=Weifeng Gao<br /> |date=2017-09-11<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=https://arxiv.org/abs/1612.06507<br /> |title=Survivable and Bandwidth Guaranteed Embe<br /> |speaker=Yuntong Zhang<br /> |date=2017-06-26<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'15<br /> |link=<br /> |title=Survivable and Bandwidth Guaranteed Embedding of Virtual Clusters in Cloud Data Centers<br /> |speaker=Yuntong Zhang<br /> |date=2017-06-26<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'15<br /> |link=https://www.sigmobile.org/mobicom/2015/papers/p9<br /> |title=Keystroke Recognition Using WiFi Signals<br /> |speaker=Weiwang Li<br /> |date=2017-06-26<br /> }}<br /> &lt;!--{{Resource:Previous_Seminars}}--&gt;<br /> <br /> ===Instructions===<br /> 请使用Latest_seminar和Hist_seminar模板更新本页信息. <br /> ** 修改时间和地点信息<br /> ** 将当前latest seminar部分的code复制到[[Resource:Previous_Seminars|这个页面]]中<br /> ** 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=<br /> ** 填入latest seminar各字段信息<br /> ** link请务必不要留空，如果没有link则填本页地址 https://mobinets.org/index.php?title=Resource:Seminar<br /> <br /> *格式说明<br /> ** Latest_seminar: <br /> &lt;blockquote&gt;&lt;small&gt;<br /> {{Latest_seminar<br /> &lt;br&gt;|confname=<br /> &lt;br&gt;|link=<br /> &lt;br&gt;|title=<br /> &lt;br&gt;|speaker=<br /> &lt;br&gt;}}<br /> &lt;/small&gt;<br /> &lt;/blockquote&gt;<br /> ** Hist_seminar<br /> &lt;blockquote&gt;&lt;small&gt;<br /> {{Hist_seminar<br /> &lt;br&gt;|confname=<br /> &lt;br&gt;|link=<br /> &lt;br&gt;|title=<br /> &lt;br&gt;|speaker=<br /> &lt;br&gt;|date=<br /> &lt;br&gt;}}<br /> &lt;/small&gt;&lt;/blockquote&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Previous_Seminars&diff=3460 2025-12-09T07:31:15Z

<p>Zhiwei: </p> <hr /> <div>=== History ===<br /> {{Hist_seminar<br /> |confname =ToN'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/10843977<br /> |title= Spliceosome: On-Camera Video Thinning and Tuning for Timely and Accurate Analytics<br /> |speaker=Zhongwei Sun<br /> |date=2025-11-28<br /> }}<br /> {{Hist_seminar<br /> |confname =ASAP'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/11113621<br /> |title= ReaLLM: A Trace-Driven Framework for Rapid Simulation of Large-Scale LLM Inference<br /> |speaker=JunZhe<br /> |date=2025-11-21<br /> }}{{Hist_seminar<br /> |abstract =With the proliferation of mobile devices, spatial crowdsourcing has emerged as a promising paradigm for facilitating location-based services, encompassing various applications across academia and industries. Recently, pioneering works have attempted to infer workers' mobility patterns from historical data to improve the quality of task assignment. However, these studies have overlooked or under-examined issues such as the dynamic mobility patterns of crowd workers, especially in the context of newcomers, the misalignment between the objectives of mobility prediction and task assignment, and the effective utilization of predicted mobility patterns. In this paper, we investigate a problem we term Task Assignment in Mobility Prediction-aware Spatial Crowdsourcing (TAMP). To address the TAMP problem, we first propose a task-adaptive meta-learning algorithm, which trains a set of specific meta-knowledge for workers' mobility prediction models through game theory-based learning task clustering and meta-training within each cluster. Then, we design a task assignment-oriented loss function and develop a task assignment algorithm that incorporates prediction performance, prioritizing assignments with higher confidence of completion. Extensive experiments on real-world datasets validate that our proposed methods can effectively improve the quality of task assignment.<br /> |confname =ICDE'25<br /> |link = https://ieeexplore.ieee.org/document/11113007<br /> |title= Effective Task Assignment in Mobility Prediction-Aware Spatial Crowdsourcing<br /> |speaker= Zhenguo<br /> |date=2025-11-21<br /> }}{{Hist_seminar<br /> |abstract = Entanglement distribution across remote distances is critical for many quantum applications. Currently, the de facto approach for remote entanglement distribution relies on optical fiber for on-the-ground entanglement distribution. However, the fiber-based approach is incapable of global-scale entanglement distribution due to intrinsic limitations. This paper investigates a new hybrid ground-satellite quantum network architecture (QuESat) for global-scale entanglement distribution, integrating an on-the-ground fiber network with a global-scale passive optical network built with low-Earth-orbit satellites. The satellite network provides dynamic construction of photon lightpaths based on near-vacuum beam guides constructed via adjustable arrays of lenses, forwarding photons from one ground station to another with very high efficiency over long distances compared to using fiber. To assess the feasibility and effectiveness of QuESat for global communication, we formulate lightpath provisioning and entanglement distribution problems, considering the orbital dynamics of satellites and the time-varying entanglement demands from ground users. A two-stage algorithm is developed to dynamically configure the beam guides and distribute entanglements, respectively. The algorithm combines randomized and deterministic rounding for lightpath provisioning to enable global connectivity, with optimal entanglement swapping for distributing entanglements to meet users' demands. By developing a ground-satellite quantum network simulator, QuESat achieves multi-fold improvements compared to repeater networks.<br /> |confname = INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/document/11044649<br /> |title= QuESat: Satellite-Assisted Quantum Internet for Global-Scale Entanglement Distribution<br /> |speaker= Yaliang<br /> |date=2025-11-07<br /> }}{{Hist_seminar<br /> |abstract =The global business of transnational enterprises demands geo-distributed databases, where the leader-follower-based consensus protocols are the key to guaranteeing consistency of replicas spread across regions. Compared with traditional databases running in a single data center, determining which node is the leader in consensus protocol has a greater per-formance impact in geo-distributed databases running across multiple data centers. However, the performance of legacy leader management is far from satisfactory due to the network and application dynamics (e.g., network delay, node popularity, operation read-write ratio). This paper proposes GeoLM toward performance-oriented leader management for geo-distributed consensus protocols. GeoLM captures the network and application dynamics and proactively conducts seamless leader handovers with bounded switching costs. Our geo-distributed experimental results show that GeoLM improves performance up to 49.75% over the baselines (e.g., Raft and Geo-Raft) and achieves considerably good performance compared to state-of-the-art consensus protocols (e.g., SwiftPaxos, CURP, and EPaxos).<br /> |confname = INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/document/11044598<br /> |title= GeoLM: Performance-oriented Leader Management for Geo-Distributed Consensus Protocol<br /> |speaker= Linqi Liu<br /> |date=2025-11-07<br /> }}{{Hist_seminar<br /> |abstract = Immersive telepresence has the potential to revolutionize remote communication by offering a highly interactive and engaging user experience. However, state-of-the-art exchanges large volumes of 3D content to achieve satisfactory visual quality, resulting in substantial Internet bandwidth consumption. To tackle this challenge, we introduce MagicStream, a first-of-its-kind semantic-driven immersive telepresence system that effectively extracts and delivers compact semantic details of captured 3D representation of users, instead of traditional bit-by-bit communication of raw content. To minimize bandwidth consumption while maintaining low end-to-end latency and high visual quality, MagicStream incorporates the following key innovations: (1) efficient extraction of user's skin/cloth color and motion semantics based on lighting characteristics and body keypoints, respectively; (2) novel, real-time human body reconstruction from motion semantics; and (3) on-the-fly neural rendering of users' immersive representation with color semantics. We implement a prototype of MagicStream and extensively evaluate its performance through both controlled experiments and user trials. Our results show that, compared to existing schemes, MagicStream can drastically reduce Internet bandwidth usage by up to 1195X while maintaining good visual quality.<br /> |confname = Sensys'24<br /> |link = https://dl.acm.org/doi/10.1145/3666025.3699344<br /> |title= MagicStream: Bandwidth-conserving Immersive Telepresence via Semantic Communication<br /> |speaker= Mengfan Wang<br /> |date=2025-10-31<br /> }}{{Hist_seminar<br /> |abstract =To fulfill computing demands of numerous Internet of Things (IoT) devices in infrastructure-free regions, low earth orbit (LEO) satellite edge computing has been proposed in recent years, to circumvent the latency arising from long backhaul and link congestion in traditional cloud computing mode. This article proposes a novel time-varying graph-based collaborative task offloading strategy for LEO satellite IoT to reduce task computing latency. To this end, a computing coordinate graph (CCG) is designed to characterize the time-varying topology and resource distribution of LEO satellite networks. When a task is offloaded to LEO satellite networks because local computing capability is unable to meet latency constraint, the position of the task access satellite in the CCG is determined first. Then, the expanded hop counts from all satellite nodes to the access satellite are calculated, which informs the partitioning of different node sets. Afterwards, considering both link and on-board computing resources, with the access satellite as the reference node, the minimum total task computing latency for each node set is obtained in an ascending order of the expanded hop counts. Finally, the minimum one among obtained latency values is the anticipated total task computing latency. Simulation results demonstrate the effectiveness of the proposed task offloading strategy in reducing task computing latency.<br /> |confname = Systems Joural<br /> |link = https://ieeexplore.ieee.org/document/11024019<br /> |title= Collaborative Task Offloading for LEO Satellite Internet of Things: A Novel Computing Coordinate Graph-Based Approach<br /> |speaker= Yifei Zhou<br /> |date=2025-10-31<br /> }}<br /> {{Hist_seminar<br /> |abstract = Unlike traditional data collection applications (e.g., environment monitoring) that are dominated by uplink transmissions, the newly emerging applications (e.g., device actuation, firmware update, packet reception acknowledgement) also pose ever-increasing demands on downlink transmission capabilities. However, current LoRaWAN falls short in supporting such applications primarily due to downlink-uplink asymmetry. While the uplink can concurrently receive multiple packets, downlink transmission is limited to a single logical channel at a time, which fundamentally hinders the deployment of downlink-hungry applications. To tackle this practical challenge, FDLoRa develops the first-of-its-kind in-band full-duplex LoRa gateway design with novel solutions to mitigate the impact of self-interference (i.e., strong downlink interference to ultra-weak uplink reception), which unleashes the full spectrum for in-band downlink transmissions without compromising the reception of weak uplink packets. Built upon the full-duplex gateways, FDLoRa introduces a new downlink framework to support concurrent downlink transmissions over multiple logical channels of available gateways. Evaluation results demonstrate that FDLoRa boosts downlink capacity by 5.7x compared to LoRaWAN on a three-gateway testbed and achieves 2.58x higher downlink concurrency per gateway than the state-of-the-art.<br /> |confname = Sensys'24<br /> |link = https://dl.acm.org/doi/10.1145/3666025.3699338<br /> |title= FDLoRa: Tackling Downlink-Uplink Asymmetry with Full-duplex LoRa Gateways<br /> |speaker= Kai Chen<br /> |date=2025-10-23<br /> }}{{Hist_seminar<br /> |abstract =Recent years have witnessed a widespread adoption of containers. While containers simplify and accelerate application development, existing container network technologies either incur significant overhead, which hurts performance for distributed applications, or lose flexibility or compatibility, which hinders the widespread deployment in production. We carefully analyze the kernel data path of an overlay network, quantifying the time consumed by each segment of the data path and identifying the extra overhead in an overlay network compared to bare metal. We observe that this extra overhead generates repetitive results among packets, which inspires us to introduce caches within an overlay network. We design and implement ONCache (Overlay Network Cache), a cache-based container overlay network, to eliminate the extra overhead while maintaining flexibility and compatibility. We implement ONCache using the extended Berkeley Packet Filter (eBPF) with only 524 lines of code, and integrate it as a plugin of Antrea. With ONCache, containers attain networking performance akin to that of bare metal. Compared to the standard overlay networks, ONCache improves throughput and request-response transaction rate by 12% and 36% for TCP (20% and 34% for UDP), respectively, while significantly reducing per-packet CPU overhead. Popular distributed applications also benefit from ONCache.<br /> |confname = NSDI'25 <br /> |link = https://www.usenix.org/conference/nsdi25/presentation/lin-shengkai<br /> |title= ONCache: A Cache-Based Low-Overhead Container Overlay Network<br /> |speaker= Daobing Zeng<br /> |date=2025-10-24<br /> }}<br /> {{Hist_seminar<br /> |abstract = We present HyperCam, an energy-efficient image classification pipeline that enables computer vision tasks onboard low-power IoT camera systems. HyperCam leverages hyperdimensional computing to perform training and inference efficiently on low-power microcontrollers. We implement a low-power wireless camera platform using off-the-shelf hardware and demonstrate that HyperCam can achieve an accuracy of 93.60%, 84.06%, 92.98%, and 72.79% for MNIST, Fashion-MNIST, Face Detection, and Face Identification tasks, respectively, while significantly outperforming other classifiers in resource efficiency. \revSpecifically, it delivers inference latency of 0.08-0.27s while using 42.91-63.00KB flash memory and 22.25KB RAM at peak. Among other machine learning classifiers such as SVM, xgBoost, MicroNets, MobileNetV3, and MCUNetV3, HyperCam is the only classifier that achieves competitive accuracy while maintaining competitive memory footprint and inference latency that meets the resource requirements of low-power camera systems.<br /> |confname = Arxiv<br /> |link = https://arxiv.org/html/2501.10547v1<br /> |title= HyperCam: Low-Power Onboard Computer Vision for IoT Cameras<br /> |speaker= Menghao Liu<br /> |date=2025-10-17<br /> }}{{Hist_seminar<br /> |abstract = We present NIER, a video conferencing system that can adaptively maintain a low bitrate (e.g., 10–100 Kbps) with reasonable visual quality while being robust to packet losses. We use key-point-based deep image animation (DIA) as a key building block and address a series of networking and system challenges to make NIER practical. Our evaluations show that NIER significantly outperforms the baseline solutions.<br /> |confname =SIGCOMM'25 (short paper)<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3718958.3750518<br /> |title= NIER: Practical Neural-enhanced Low-bitrate Video Conferencing<br /> |speaker=Xinyan Wang<br /> |date=2025-9-26<br /> }}{{Hist_seminar<br /> |abstract = Distributed Edge Computing (DEC) has emerged as a novel paradigm, owing to its superior performance in communication latency, parallel computing efficiency, and energy consumption. With the surge of tasks in generative artificial intelligence, DEC faces higher demands for parallel computing efficiency. Scheduling multiple tasks for simultaneous processing, rather than one-by-one handling, could enhance parallel efficiency. Multiple tasks have multi-dependencies, i.e., sequence dependency, attribute similarity, and attribute correlation. Utilizing the bidirectional edges of traditional graphs to represent multi-dependencies can lead to an explosion in quantity. A hypergraph, with its hyperedges capable of connecting any number of vertices, can significantly solve the above problem. However, the multi-dependencies are rarely studied in the current research, posing the challenges, including incapable representing and unable capturing of multi-dependency hypergraph. In this work, we introduce a Joint communication and computation scheduling for hypErgraph Tasks in DEC, namely HypeJet, To effectively represent multi-dependencies, we employ hypergraph construction to represent task attributes and utilize hypergraph partitioning to clarify and refine task attribute correlations, enhancing parallel efficiency. In response to the challenge of capturing multi-dependencies, we employ a scheduling mechanism with the hypergraph neural network that efficiently acquires higher-order attribute correlated information among convolution matrices, providing enriched contextual information on multi-dependencies that supports decision-making in scheduling tasks. The evaluations using real-world traces demonstrate an 18.07% improvement in parallel efficiency of task scheduling.<br /> |confname =INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/11044587<br /> |title= HyperJet: Joint Communication and Computation Scheduling for Hypergraph Tasks in Distributed Edge Computing<br /> |speaker= Yi Zhou<br /> |date=2025-9-26<br /> }}{{Hist_seminar<br /> |abstract = Localization of networked nodes is an essential problem in emerging applications, including first-responder navigation, automated manufacturing lines, vehicular and drone navigation, asset tracking, Internet of Things, and 5G communication networks. In this paper, we present Locate3D, a novel system for peer-to-peer node localization and orientation estimation in large networks. Unlike traditional range-only methods, Locate3D introduces angle-of-arrival (AoA) data as an added network topology constraint. The system solves three key challenges: it uses angles to reduce the number of measurements required by 4× and jointly uses range and angle data for location estimation. We develop a spanning-tree approach for fast location updates, and to ensure the output graphs are rigid and uniquely realizable, even in occluded or weakly connected areas. Locate3D cuts down latency by up to 75% without compromising accuracy, surpassing standard range-only solutions. It has a 0.86 meter median localization error for building-scale multi-floor networks (32 nodes, 0 anchors) and 12.09 meters for large-scale networks (100,000 nodes, 15 anchors).<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/garg<br /> |title= Large Network UWB Localization: Algorithms and Implementation<br /> |speaker=Bangguo<br /> |date=2025-9-26<br /> }}<br /> {{Hist_seminar<br /> |abstract = With cloud-side computing and rendering, mobile cloud gaming (MCG) is expected to deliver high-quality gaming experiences to budget mobile devices. However, our measurement on representative MCG platforms reveals that even under good network conditions, all platforms exhibit high interactive latency of 112–403 ms, from a user-input action to its display response, that critically affects users’ quality of experience. Moreover, jitters in network latency often lead to significant fluctuations in interactive latency. In this work, we collaborate with a commercial MCG platform to conduct the first in-depth analysis on the interactive latency of cloud gaming. We identify VSync, the synchronization primitive of Android graphics pipeline, to be a key contributor to the excessive interactive latency; as many as five VSync events are intricately invoked, which serialize the complex graphics processing logic on both the client and cloud sides. To address this, we design an end-to-end VSync regulator, dubbed LoopTailor, which minimizes VSync events by decoupling game rendering from the lengthy cloud-side graphics pipeline and coordinating cloud game rendering directly with the client. We implement LoopTailor on the collaborated platform and commodity Android devices, reducing the interactive latency (by ∼34%) to stably below 100 ms.<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/li-yang<br /> |title= Dissecting and Streamlining the Interactive Loop of Mobile Cloud Gaming<br /> |speaker= Li Chen<br /> |date=2025-9-9<br /> }}{{Hist_seminar<br /> |abstract = The local deployment of large language models (LLMs) on mobile devices has garnered increasing attention due to its advantages in enhancing user privacy and enabling offline operation. However, given the limited computational resources of a single mobile device, only small language models (SLMs) with restricted capabilities can currently be supported. In this paper, we explore the potential of leveraging the collective computing power of multiple mobile devices to collaboratively support more efficient local LLM inference. We evaluate the feasibility and efficiency of existing parallelism techniques under the constraints of mobile devices and wireless network, identifying that chunked pipeline parallelism holds promise for realizing this vision. Building on this insight, we propose FlexSpark, a novel solution designed to achieve efficient and robust multi-device collaborative inference. FlexSpark incorporates priority scheduling, ordered communication, and elastic compression to maximize wireless bandwidth utilization, and thus accelerates distributed inference. Preliminary experimental results demonstrate that FlexSpark achieves up to a 2 × speedup compared to state-of-the-art frameworks, significantly enhancing the practicality and scalability of LLM deployment on mobile devices.<br /> |confname =APNet'25<br /> |link = https://dl.acm.org/doi/10.1145/3735358.3735368<br /> |title= FlexSpark: Robust and Efficient Multi-Device Collaborative Inference over Wireless Network<br /> |speaker=Ruizhen<br /> |date=2025-9-19<br /> }}<br /> {{Hist_seminar<br /> |abstract = Reconfigurable Intelligent Surfaces (RIS) are a promising technology for creating smart radio environments by controlling wireless propagation. However, several factors hinder the integration of RIS technology into existing cellular networks, including the incompatibility of RIS control interfaces with 5G PHY/MAC procedures for synchronizing radio scheduling decisions and RIS operation, and the cost and energy limitations of passive RIS technology. This paper presents RISENSE, a system for practical RIS integration in cellular networks. First, we propose a novel, low-cost, and low-power RIS design capable of decoding control messages without complex baseband operations or additional RF chains, utilizing a power sensor and a network of microstrip lines and couplers. Second, we design an effective in-band wireless RIS control interface, compatible with 5G PHY/MAC procedures, that embeds amplitude-modulated (AM) RIS control commands directly into standard OFDM-modulated 5G data channels. Finally, we propose a low-overhead protocol that supports swift on-demand RIS re-con gurability, making it adaptable to varying channel conditions and user mobility, while minimizing the wastage of 5G OFDM symbols. Our experiments validate the design of RISENSE and our evaluation shows that our system can reconfigure a RIS at the same pace as users move, boosting 5G coverage where static or slow RIS controllers cannot.<br /> |confname = Mobisys'25<br /> |link = https://dspace.networks.imdea.org/handle/20.500.12761/1925<br /> |title= RISENSE: Long-Range In-Band Wireless Control of Passive Reconfigurable Intelligent Surfaces<br /> |speaker= Haifeng<br /> |date=2025-9-12<br /> }}<br /> {{Hist_seminar<br /> |abstract = Traditional 3D content representations include dense point clouds that consume large amounts of data and hence network bandwidth, while newer representations such as neural radiance fields suffer from poor frame rates due to their non-standard volumetric rendering pipeline. 3D Gaussian splats (3DGS) can be seen as a generalization of point clouds that meet the best of both worlds, with high visual quality and efficient rendering for real-time frame rates. However, delivering 3DGS scenes from a hosting server to client devices is still challenging due to high network data consumption (e.g., 1.5 GB for a single scene). The goal of this work is to create an efficient 3D content delivery framework that allows users to view high quality 3D scenes with 3DGS as the underlying data representation. The main contributions of the paper are: (1) Creating new layered 3DGS scenes for efficient delivery, (2) Scheduling algorithms to choose what splats to download at what time, and (3) Trace-driven experiments from users wearing virtual reality headsets to evaluate the visual quality and latency. Our system for Layered 3D Gaussian Splats delivery (L3GS) demonstrates high visual quality, achieving 16.9% higher average SSIM compared to baselines, and also works with other compressed 3DGS representations. The code is available at https://github.com/mavens-lab/layered_3d_gaussian_splats.<br /> |confname =Mobicom'25<br /> |link = https://arxiv.org/html/2504.05517v1<br /> |title= L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery<br /> |speaker=Jiyi<br /> |date=2025-9-12<br /> }}<br /> {{Hist_seminar<br /> |abstract = This year, we are embracing the exciting new trends in AIoT including MLsys, LLMs, embodied perception, volumetric videos, etc. Papers collected from top venues in 2025 will be discussed in-depth, and research problems and new ideas are to be discovered!<br /> |confname = Begin of new semester<br /> |link = https://mobinets.cn/site/Resource:Paper_Carnival_2025<br /> |title= Paper Carnival 2025<br /> |speaker=All<br /> |date=2025-08-27<br /> }}<br /> {{Hist_seminar<br /> |abstract = In the metaverse era, point cloud video (PCV) streaming on mobile XR devices is pivotal. While most current methods focus on PCV compression from traditional 3-DoF video services, emerging AI techniques extract vital semantic information, producing content resembling the original. However, these are early-stage and computationally intensive. To enhance the inference efficacy of AI-based approaches, accommodate dynamic environments, and facilitate applicability to metaverse XR devices, we present ISCom, an interest-aware semantic communication scheme for lightweight PCV streaming. ISCom is featured with a region-of-interest (ROI) selection module, a lightweight encoder-decoder training module, and a learning-based scheduler to achieve real-time PCV decoding and rendering on resource-constrained devices. ISCom&amp;#x2019;s dual-stage ROI selection provides significantly reduces data volume according to real-time interest. The lightweight PCV encoder-decoder training is tailored to resource-constrained devices and adapts to the heterogeneous computing capabilities of devices. Furthermore, We provide a deep reinforcement learning (DRL)-based scheduler to select optimal encoder-decoder model for various devices adaptivelly, considering the dynamic network environments and device computing capabilities. Our extensive experiments demonstrate that ISCom outperforms baselines on mobile devices, achieving a minimum rendering frame rate improvement of 10 FPS and up to 22 FPS. Furthermore, our method significantly reduces memory usage by 41.7&amp;#x0025; compared to the state-of-the-art AITransfer method. These results highlight the effectiveness of ISCom in enabling lightweight PCV streaming and its potential to improve immersive experiences for emerging metaverse application.<br /> |confname =JSAC'24<br /> |link = https://dl.acm.org/doi/10.1109/JSAC.2023.3345430<br /> |title= ISCom: Interest-Aware Semantic Communication Scheme for Point Cloud Video Streaming on Metaverse XR Devices<br /> |speaker=Jiyi<br /> |date=2025-06-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = Scientific Illustration Tutorial<br /> |confname = TUTORIAL<br /> |link = https://mobinets.cn/Resource:Seminar<br /> |title= Idea share<br /> |speaker=OldBee<br /> |date=2025-06-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = Deploying deep convolutional neural networks (CNNs) for edge-based video analytics poses significant challenges due to the intensive computing demands. Model partitioning has emerged as a promising solution by offloading segments of CNNs to multiple proximal edge devices for collaborative inference. However, this approach often incurs substantial cross-device transmission overhead, particularly in handling intermediate feature maps. To address these limitations, we propose ReDream (REsidual feature-DRivEn mixed spArse coding for Model partitioning), a novel edge-centric video analytics framework that jointly optimizes transmission efficiency and inference accuracy. ReDream introduces two key innovations: 1) It enhances the sparsity of intermediate features by replacing activation functions with ReLU in selected CNN layers and retraining, thereby increasing the proportion of zero-valued elements. 2) It leverages the heterogeneous distribution of feature data across layers by applying a mixed sparse coding scheme, i.e., selecting different compression methods adaptively to optimize model partitioning. These optimizations enable ReDream to support more efficient cross-device inference while maintaining high model accuracy, making it well-suited for real-time deployment in collaborative edge environments.<br /> |confname = IDEA<br /> |link = https://mns.uestc.cn/wiki/Research:InProgress/MixedSparseCoding<br /> |title= ReDream: Residual Feature-Driven Mixed Sparse Coding for Model Partitioning<br /> |speaker=Xianyang<br /> |date=2025-05-23<br /> }}<br /> {{Hist_seminar<br /> |abstract = While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adopting context-awareness i.e. narrowing down a classification task to the current deployment context consisting of only recent inference queries can substantially enhance performance in resource-constrained environments. We propose a new paradigm, CACTUS, for scalable and efficient context-aware classification where a micro-classifier recognizes a small set of classes relevant to the current context and, when context change happens (e.g., a new class comes into the scene), rapidly switches to another suitable micro-classifier. CACTUS features several innovations, including optimizing the training cost of context-aware classifiers, enabling on-the-fly context-aware switching between classifiers, and balancing context switching costs and performance gains via simple yet effective switching policies. We show that CACTUS achieves significant benefits in accuracy, latency, and compute budget across a range of datasets and IoT platforms.<br /> |confname = Mobisys'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3643832.3661888<br /> |title= CACTUS: Dynamically Switchable Context-aware micro-Classifiers for Efficient IoT Inference<br /> |speaker= Zhenhua<br /> |date=2025-04-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Nowadays, volumetric videos have emerged as an attractive multimedia application providing highly immersive watching experiences since viewers could adjust their viewports at 6 degrees-of-freedom. However, the point cloud frames composing the video are prohibitively large, and effective compression techniques should be developed. There are two classes of compression methods. One suggests exploiting the conventional video codecs (2D-based methods) and the other proposes to compress the points in 3D space directly (3D-based methods). Though the 3D-based methods feature fast coding speeds, their compression ratios are low since the failure of leveraging inter-frame redundancy. To resolve this problem, we design a patch-wise compression framework working in the 3D space. Specifically, we search rigid moves of patches via the iterative closest point algorithm and construct a common geometric structure, which is followed by color compensation. We implement our decoder on a GPU platform so that real-time decoding and rendering are realized. We compare our method with GROOT, the state-of-the-art 3D-based compression method, and it reduces the bitrate by up to 5.98×. Moreover, by trimming invisible content, our scheme achieves comparable bandwidth demand of V-PCC, the representative 2D-based method, in FoV-adaptive streaming.<br /> |confname = TC'24<br /> |link = https://ieeexplore.ieee.org/document/10360355<br /> |title= A GPU-Enabled Real-Time Framework for Compressing and Rendering Volumetric Videos<br /> |speaker=Mengfan<br /> |date=2025-04-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing their private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE does not consider the heterogeneity among different clients, an intrinsic problem in cross-silo FL, often resulting in undermined training efficiency with slow convergence and stragglers. In this work, we propose FedPHE, an efficiently packed homomorphically encrypted FL framework with secure weighted aggregation and client selection to tackle the heterogeneity problem. Specifically, using CKKS with sparsification, FedPHE can achieve efficient encrypted weighted aggregation by accounting for contributions of local updates to the global model. To mitigate the straggler effect, we devise a sketching-based client selection scheme to cherry-pick representative clients with heterogeneous models and computing capabilities. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients’ privacy, achieve a training speedup of 1.85 − 4.44×, cut the communication overhead by 1.24 − 22.62× , and reduce the straggler effect by up to 1.71 − 2.39×.<br /> |confname =INFOCOM24'<br /> |link = https://ieeexplore.ieee.org/abstract/document/10621440<br /> |title= Efficient and Straggler-Resistant Homomorphic Encryption for Heterogeneous Federated Learning<br /> |speaker=Dongting<br /> |date=2025-03-28<br /> }}{{Hist_seminar<br /> |abstract = Entanglement routing (ER) in quantum networks must guarantee entanglement fidelity, a property that is crucial for applications such as quantum key distribution, quantum computation, and quantum sensing. Conventional ER approaches assume that network links can only generate entanglements with a fixed fidelity, and then they rely on purification to improve endto-end fidelities. However, recent advances in entanglement generation technologies show that quantum links can be configured by choosing among different fidelity/entanglement-rate combinations (defined in this paper as link configurations), hence enabling a more flexible assignment of quantum-network resources for meeting specific application requirements. To exploit this opportunity, we introduce the problem of link configuration for fidelityconstrained routing and purification (LC-FCRP) in Quantum Networks. We first formulate a simplified FCRP version as a Mixed Integer Linear Programming (MILP) model, where the link fidelity can be adjusted within a finite set. Then, to explore the full space of possible link configurations, we propose a link configuration algorithm based on a novel shortest-pathbased fidelity determination (SPFD) algorithm w/o Bayesian Optimization, which can be applied on top of any existing ER algorithm. Numerical results demonstrate that link configuration improves the acceptance ratio of existing ER algorithms by 87%.<br /> |confname =INFOCOM25'<br /> |link = https://re.public.polimi.it/bitstream/11311/1281986/1/final_infocom25_link_configuration_for_entanglement_routing.pdf<br /> |title= Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks<br /> |speaker=Yaliang<br /> |date=2025-03-27<br /> }}<br /> {{Hist_seminar<br /> |abstract = Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains. Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities. This typically involves extensive sampling at inference time guided by an external LLM verifier, resulting in a two-player system. Despite external guidance, the effectiveness of this system demonstrates the potential of a single LLM to tackle complex tasks. Thus, we pose a new research problem: Can we internalize the searching capabilities to fundamentally enhance the reasoning abilities of a single LLM? This work explores an orthogonal direction focusing on post-training LLMs for autoregressive searching (i.e., an extended reasoning process with self-reflection and self-exploration of new strategies). To achieve this, we propose the Chain-of-Action-Thought (COAT) reasoning and a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning. Our approach results in Satori, a 7B LLM trained on open-source models and data. Extensive empirical evaluations demonstrate that Satori achieves state-of-the-art performance on mathematical reasoning benchmarks while exhibits strong generalization to out-of-domain tasks. Code, data, and models will be fully open-sourced.<br /> |confname = Arxiv<br /> |link = https://arxiv.org/abs/2502.02508<br /> |title= Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search<br /> |speaker=Qinyong<br /> |date=2025-03-14<br /> }}{{Hist_seminar<br /> |abstract = Light bulbs have been recently explored to design Light Fidelity (LiFi) communication to battery-free tags, thus complementing Radiofrequency (RF) backscatter in the uplink. In this paper, we show that LiFi and RF backscatter are complementary and have unexplored interactions. We introduce PassiveLiFi, a battery-free system that uses LiFi to transmit RF backscatter at a meagre power budget. We address several challenges on the system design in the LiFi transmitter, the tag and the RF receiver. We design the first LiFi transmitter that implements a chirp spread spectrum (CSS) using the visible light spectrum. We use a small bank of solar cells for both communication and harvesting, and reconfigure them based on the amount of harvested energy and desired data rate. We further alleviate the low responsiveness of solar cells with a new low-power receiver design in the tag. We design and implement a novel technique for embedding multiple symbols in the RF backscatter based on delayed chirps. Experimental results with an RF carrier of 17dBm show that we can generate RF backscatter with a range of 92.1 meters/ μW consumed in the tag, which is almost double with respect to prior work.<br /> |confname =ToN'23<br /> |link = https://ieeexplore.ieee.org/document/10371205/<br /> |title= LiFi for Low-Power and Long-Range RF Backscatter<br /> |speaker=Mengyu<br /> |date=2025-03-14<br /> }}<br /> {{Hist_seminar<br /> |abstract = Video analytics is widespread in various applications serving our society. Recent advances of content enhancement in video analytics offer significant benefits for the bandwidth saving and accuracy improvement. However, existing content-enhanced video analytics systems are excessively computationally expensive and provide extremely low throughput. In this paper, we present region-based content enhancement, that enhances only the important regions in videos, to improve analytical accuracy. Our system, RegenHance, enables high-accuracy and high-throughput video analytics at the edge by 1) a macroblock-based region importance predictor that identifies the important regions fast and precisely, 2) a region-aware enhancer that stitches sparsely distributed regions into dense tensors and enhances them efficiently, and 3) a profile-based execution planer that allocates appropriate resources for enhancement and analytics components. We prototype RegenHance on five heterogeneous edge devices. Experiments on two analytical tasks reveal that region-based enhancement improves the overall accuracy of 10-19% and achieves 2-3x throughput compared to the state-of-the-art frame-based enhancement methods.<br /> |confname =NSDI'25<br /> |link = https://arxiv.org/pdf/2407.16990<br /> |title= Region-based Content Enhancement for Efficient Video Analytics at the Edge<br /> |speaker=Xinyan<br /> |date=2025-03-07<br /> }}{{Hist_seminar<br /> |abstract = Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at this https URL<br /> |confname =AAAI'22<br /> |link = https://arxiv.org/abs/2112.02466<br /> |title= Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer<br /> |speaker=Bairong<br /> |date=2025-03-07<br /> }}<br /> {{Hist_seminar<br /> |abstract = The emerging programmable networks sparked significant research on Intelligent Network Data Plane (INDP), which achieves learning-based traffic analysis at line-speed. Prior art in INDP focus on deploying tree/forest models on the data plane. We observe a fundamental limitation in tree-based INDP approaches: although it is possible to represent even larger tree/forest tables on the data plane, the flow features that are computable on the data plane are fundamentally limited by hardware constraints. In this paper, we present BoS to push the boundaries of INDP by enabling Neural Network (NN) driven traffic analysis at line-speed. Many types of NNs (such as Recurrent Neural Network (RNN), and transformers) that are designed to work with sequential data have advantages over tree-based models, because they can take raw network data as input without complex feature computations on the fly. However, the challenge is significant: the recurrent computation scheme used in RNN inference is fundamentally different from the match-action paradigm used on the network data plane. BoS addresses this challenge by (i) designing a novel data plane friendly RNN architecture that can execute unlimited RNN time steps with limited data plane stages, effectively achieving line-speed RNN inference; and (ii) complementing the on-switch RNN model with an off-switch transformer-based traffic analysis module to further boost the overall performance. We implement a prototype of BoS using a P4 programmable switch as our data plane, and extensively evaluate it over multiple traffic analysis tasks. The results show that BoS outperforms state-of-the-art in both analysis accuracy and scalability..<br /> |confname =NSDI'24<br /> |link = https://www.usenix.org/conference/nsdi24/presentation/yan<br /> |title= Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed<br /> |speaker=Youwei<br /> |date=2025-02-28<br /> }}<br /> {{Hist_seminar<br /> |abstract = Recent advances in quantum information science enabled the development of quantum communication network prototypes and created an opportunity to study full-stack quantum network architectures. This work develops SeQUeNCe, a comprehensive, customizable quantum network simulator. Our simulator consists of five modules: hardware models, entanglement management protocols, resource management, network management, and application. This framework is suitable for simulation of quantum network prototypes that capture the breadth of current and future hardware technologies and protocols. We implement a comprehensive suite of network protocols and demonstrate the use of SeQUeNCe by simulating a photonic quantum network with nine routers equipped with quantum memories. The simulation capabilities are illustrated in three use cases. We show the dependence of quantum network throughput on several key hardware parameters and study the impact of classical control message latency. We also investigate quantum memory usage efficiency in routers and demonstrate that redistributing memory according to anticipated load increases network capacity by 69.1% and throughput by 6.8%. We design SeQUeNCe to enable comparisons of alternative quantum network technologies, experiment planning, and validation and to aid with new protocol design. We are releasing SeQUeNCe as an open source tool and aim to generate community interest in extending it.<br /> |confname =IOPSCIENCE'21<br /> |link = https://iopscience.iop.org/article/10.1088/2058-9565/ac22f6/meta<br /> |title= SeQUeNCe: a customizable discrete-event simulator of quantum networks<br /> |speaker=Junzhe<br /> |date=2025-02-21<br /> }}{{Hist_seminar<br /> |abstract = This article proposes a remote environmental monitoring system based on low-power Internet of Things, which is applied in smart agriculture to achieve remote and real-time measurement of temperature, humidity, and light intensity parameters in the crop growth environment within the coverage range of the device The system adopts low-power Internet of Things technology, which has the characteristics of wide coverage, multiple connections, fast speed, low cost, low power consumption, and excellent architecture. The overall design of the system includes multiple environmental monitoring nodes, a LoRa gateway, and corresponding environmental monitoring upper computer software. In terms of system software, it involves programming of node MCU and client upper computer software. The key technology implementation includes the hardware design and implementation of low-power sensor nodes and the development of LoRa protocol. System testing and performance analysis show that the optimized LoRa protocol performs well in communication distance, power consumption, stability, and other aspects, laying the foundation for the efficient operation of the system. This study provides a powerful tool for sustainable resource management, which helps to promote agricultural modernization and rural revitalization.<br /> |confname =CISCE'24<br /> |link = https://ieeexplore.ieee.org/abstract/document/10653076<br /> |title= A Long Distance Environmental Monitoring System Based on Low Power IoT<br /> |speaker= Ayesha Rasool<br /> |date=2025-02-21<br /> }}<br /> {{Hist_seminar<br /> |abstract = Recently, smart roadside infrastructure (SRI) has demonstrated the potential of achieving fully autonomous driving systems. To explore the potential of infrastructure-assisted autonomous driving, this paper presents the design and deployment of Soar, the first end-to-end SRI system specifically designed to support autonomous driving systems. Soar consists of both software and hardware components carefully designed to overcome various system and physical challenges. Soar can leverage the existing operational infrastructure like street lampposts for a lower barrier of adoption. Soar adopts a new communication architecture that comprises a bi-directional multi-hop I2I network and a downlink I2V broadcast service, which are designed based on off-the-shelf 802.11ac interfaces in an integrated manner. Soar also features a hierarchical DL task management framework to achieve desirable load balancing among nodes and enable them to collaborate efficiently to run multiple data-intensive autonomous driving applications. We deployed a total of 18 Soar nodes on existing lampposts on campus, which have been operational for over two years. Our real-world evaluation shows that Soar can support a diverse set of autonomous driving applications and achieve desirable real-time performance and high communication reliability. Our findings and experiences in this work offer key insights into the development and deployment of next-generation smart roadside infrastructure and autonomous driving systems.<br /> |confname =MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3649352<br /> |title= Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving<br /> |speaker=Jiahao<br /> |date=2025-01-10<br /> }}{{Hist_seminar<br /> |abstract = GPUs are increasingly utilized for running DNN tasks on emerging mobile edge devices. Beyond accelerating single task inference, their value is also particularly apparent in efficiently executing multiple DNN tasks, which often have strict latency requirements in applications. Preemption is the main technology to ensure multitasking timeliness, but mobile edges primarily offer two priorities for task queues, and existing methods thus achieve only coarse-grained preemption by categorizing DNNs into real-time and best-effort, permitting a real-time task to preempt best-effort ones. However, the efficacy diminishes significantly when other real-time tasks run concurrently, but this is already common in mobile edge applications. Due to different hardware characteristics, solutions from other platforms are unsuitable. For instance, GPUs on traditional mobile devices primarily assist CPU processing and lack special preemption support, mainly following FIFO in GPU scheduling. Clouds handle concurrent task execution, but focus on allocating one or more GPUs per complex model, whereas on mobile edges, DNNs mainly vie for one GPU. This paper introduces Pantheon, designed to offer fine-grained preemption, enabling real-time tasks to preempt each other and best-effort tasks. Our key observation is that the two-tier GPU stream priorities, while underexplored, are sufficient. Efficient preemption can be realized through software design by innovative scheduling and novel exploitation of the nested redundancy principle for DNN models. Evaluation on a diverse set of DNNs shows substantial improvements in deadline miss rate and accuracy of Pantheon over state-of-the-art methods.<br /> |confname =MobiSys'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3643832.3661878<br /> |title= Pantheon: Preemptible Multi-DNN Inference on Mobile Edge GPUs<br /> |speaker=Jiale<br /> |date=2025-01-10<br /> }}<br /> {{Hist_seminar<br /> |abstract = Volumetric videos offer a unique interactive experience and have the potential to enhance social virtual reality and telepresence. Streaming volumetric videos to multiple users remains a challenge due to its tremendous requirements of network and computation resources. In this paper, we develop MuV2, an edge-assisted multi-user mobile volumetric video streaming system to support important use cases such as tens of students simultaneously consuming volumetric content in a classroom. MuV2 achieves high scalability and good streaming quality through three orthogonal designs: hybridizing direct streaming of 3D volumetric content with remote rendering, dynamically sharing edge-transcoded views across users, and multiplexing encoding tasks of multiple transcoding sessions into a limited number of hardware encoders on the edge. MuV2 then integrates the three designs into a holistic optimization framework. We fully implement MuV2 and experimentally demonstrate that MuV2 can deliver high-quality volumetric videos to over 30 concurrent untethered mobile devices with a single WiFi access point and a commodity edge server.<br /> |confname =MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3649364<br /> |title= MuV2: Scaling up Multi-user Mobile Volumetric Video Streaming via Content Hybridization and Sharing<br /> |speaker=Jiyi<br /> |date=2025-01-03<br /> }}{{Hist_seminar<br /> |abstract = The advent of 5G promises high bandwidth with the introduction of mmWave technology recently, paving the way for throughput-sensitive applications. However, our measurements in commercial 5G networks show that frequent handovers in 5G, due to physical limitations of mmWave cells, introduce significant under-utilization of the available bandwidth. By analyzing 5G link-layer and TCP traces, we uncover that improper interactions between these two layers causes multiple inefficiencies during handovers. To mitigate these, we propose M2HO, a novel device-centric solution that can predict and recognize different stages of a handover and perform state-dependent mitigation to markedly improve throughput. M2HO is transparent to the firmware, base stations, servers, and applications. We implement M2HO and our extensive evaluations validate that it yields significant improvements in TCP throughput with frequent handovers.<br /> |confname =MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3690680<br /> |title= M2HO: Mitigating the Adverse Effects of 5G Handovers on TCP<br /> |speaker=Jiacheng<br /> |date=2025-01-03<br /> }}<br /> ====2024====<br /> {{Hist_seminar<br /> |abstract = Packet routing in virtual networks requires virtual-to-physical address translation. The address mappings are updated by a single party, i.e., the network administrator, but they are read by multiple devices across the network when routing tenant packets. Existing approaches face an inherent read-write performance tradeoff: they either store these mappings in dedicated gateways for fast updates at the cost of slower forwarding or replicate them at end-hosts and suffer from slow updates.SwitchV2P aims to escape this tradeoff by leveraging the network switches to transparently cache the address mappings while learning them from the traffic. SwitchV2P brings the mappings closer to the sender, thus reducing the first packet latency and translation overheads, while simultaneously enabling fast mapping updates, all without changing existing routing policies and deployed gateways. The topology-aware data-plane caching protocol allows the switches to transparently adapt to changing network conditions and varying in-switch memory capacity.Our evaluation shows the benefits of in-network address mapping, including an up to 7.8× and 4.3× reduction in FCT and first packet latency respectively, and a substantial reduction in translation gateway load. Additionally, SwitchV2P achieves up to a 1.9× reduction in bandwidth overheads and requires order-of-magnitude fewer gateways for equivalent performance.<br /> |confname =SIGCOMM'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3651890.3672213<br /> |title= In-Network Address Caching for Virtual Networks<br /> |speaker=Dongting<br /> |date=2024-12-06<br /> }}{{Hist_seminar<br /> |abstract = Visible light communication (VLC) has become an important complementary means to electromagnetic communications due to its freedom from interference. However, existing Internet-of-Things (IoT) VLC links can reach only &lt;10 meters, which has significantly limited the applications of VLC to the vast and diverse scenarios. In this paper, we propose ChirpVLC, a novel modulation method to prolong VLC distance from ≤10 meters to over 100 meters. The basic idea of ChirpVLC is to trade throughput for prolonged distance by exploiting Chirp Spread Spectrum (CSS) modulation. Specifically, 1) we modulate the luminous intensity as a sinusoidal waveform with a linearly varying frequency and design different spreading factors (SF) for different environmental conditions. 2) We design range adaptation scheme for luminance sensing range to help receivers achieve better signal-to-noise ratio (SNR). 3) ChirpVLC supports many-to-one and non-line-of-sight communications, breaking through the limitations of visible light communication. We implement ChirpVLC and conduct extensive real-world experiments. The results show that ChirpVLC can extend the transmission distance of 5W COTS LEDs to over 100 meters, and the distance/energy utility is increased by 532% compared to the existing work.<br /> |confname = IDEA<br /> |link = https://uestc.feishu.cn/file/Pbq3bWgKJoTQObx79f3cf6gungb<br /> |title= ChirpVLC：Extending The Distance of Low-cost Visible Light Communication with CSS Modulation<br /> |speaker=Mengyu<br /> |date=2024-12-06<br /> }}<br /> {{Hist_seminar<br /> |abstract = On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. However, the intensive training workload and limited onboard computing resources pose significant challenges to the availability and efficiency of model training. While existing works address these challenges through native resource management optimization, we instead leverage our observation that edge environments usually comprise a rich set of accompanying trusted edge devices with idle resources beyond a single terminal. We propose Asteroid, a distributed edge training system that breaks the resource walls across heterogeneous edge devices for efficient model training acceleration. Asteroid adopts a hybrid pipeline parallelism to orchestrate distributed training, along with a judicious parallelism planning for maximizing throughput under certain resource constraints. Furthermore, a fault-tolerant yet lightweight pipeline replay mechanism is developed to tame the device-level dynamics for training robustness and performance stability. We implement Asteroid on heterogeneous edge devices with both vision and language models, demonstrating up to 12.2× faster training than conventional parallelism methods and 2.1× faster than state-of-the-art hybrid parallelism methods through evaluations. Furthermore, Asteroid can recover training pipeline 14× faster than baseline methods while preserving comparable throughput despite unexpected device exiting and failure.<br /> |confname = MobiCom'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3636534.3649363<br /> |title= Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices<br /> |speaker=Congrong<br /> |date=2024-11-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = The need for cooperation among intelligent edge devices has popularized cooperative multi-agent reinforcement learning (MARL) in multi-target coverage. However, many research efforts rely heavily on parameter sharing among homogeneous agents, which hampers coverage performance. The heterogeneity of computing and sensing capabilities, along with the time-varying dynamics of computing resources, pose significant challenges. To address these challenges, we propose a resource-sensitive multi-agent reinforcement learning framework based on heterogeneous edge devices (SmartHE). SmartHE decomposes the target coverage task into two hierarchical levels: 1) Executor-level task: A central coordinator assigns a subset of executors (i.e., cameras or agents) to execute action policies, aiming to minimize overall policy inference time and energy consumption by leveraging resource heterogeneity. 2) Target-level task: Each executor ignores irrelevant targets that fall outside the coverage radius of the executor based on the estimated target states and ignores redundant targets that could be more effectively covered by other executors based on the utility estimation. This enables each executor to focus on extracting features that optimize coverage. Through this dual-task framework, SmartHE efficiently improves the system performance.<br /> |confname = IDEA<br /> |link = https://mobinets.cn/site/Resource:Seminar<br /> |title= SmartHE: Resource-sensitive MARL framework based on heterogeneous edge devices<br /> |speaker=Xianyang<br /> |date=2024-11-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = Collaborative inference is the current state-of-the-art solution for mobile-server neural network inference offloading. However, we find that existing collaborative inference solutions only focus on partitioning the DNN computation, which is only a small part of achieving an efficient DNN offloading system. What ultimately determines the performance of DNN offloading is how the execution system utilizes the characteristics of the given DNN offloading task on the mobile, network, and server resources of the offloading environment. To this end, we design CoActo, a DNN execution system built from the ground up for mobile-server inference offloading. Our key design philosophy is Coactive Inference Offloading, which is a new, improved concept of DNN offloading that adds two properties, 1) fine-grained expression of DNNs and 2) concurrency of runtime resources, to existing collaborative inference. In CoActo, system components go beyond simple model splitting of existing approaches and operate more proactively to achieve the coactive execution of inference workloads. CoActo dynamically schedules concurrent interleaving of the mobile, server, and network operations to actively increase resource utilization, enabling lower end-to-end latency. We implement CoActo for various mobile devices and server environments and evaluate our system with distinct environment settings and DNN models. The experimental results show that our system achieves up to 2.1 times speed-up compared to the state-of-the-art collaborative inference solutions.<br /> |confname = Mobisys'24<br /> |link = https://dl.acm.org/doi/10.1145/3643832.3661885<br /> |title= CoActo: CoActive Neural Network Inference Offloading with Fine-grained and Concurrent Execution<br /> |speaker=Zhenhua<br /> |date=2024-11-22<br /> }}<br /> {{Hist_seminar<br /> |abstract = Caching is an indispensable technique for low-cost and fast data serving. The eviction algorithm, at the heart of a cache, has been primarily designed to maximize efficiency—reducing the cache miss ratio. Many eviction algorithms have been designed in the past decades. However, they all trade off throughput, simplicity, or both for higher efficiency. Such a compromise often hinders adoption in production systems.This work presents SIEVE, an algorithm that is simpler than LRU and provides better than state-of-the-art efficiency and scalability for web cache workloads. We implemented SIEVE in five production cache libraries, requiring fewer than 20 lines of code changes on average. Our evaluation on 1559 cache traces from 7 sources shows that SIEVE achieves up to 63.2% lower miss ratio than ARC. Moreover, SIEVE has a lower miss ratio than 9 state-of-the-art algorithms on more than 45% of the 1559 traces, while the next best algorithm only has a lower miss ratio on 15%. SIEVE's simplicity comes with superior scalability as cache hits require no locking. Our prototype achieves twice the throughput of an optimized 16-thread LRU implementation. SIEVE is more than an eviction algorithm; it can be used as a cache primitive to build advanced eviction algorithms just like FIFO and LRU.<br /> |confname =NSDI'24<br /> |link = https://www.usenix.org/conference/nsdi24/presentation/zhang-yazhuo<br /> |title= SIEVE is Simpler than LRU: an Efficient Turn-Key Eviction Algorithm for Web Caches<br /> |speaker=Haotian<br /> |date=2024-11-22<br /> }}<br /> {{Hist_seminar<br /> |abstract = In this paper, we revisit the problem of the current routing system in terms of prediction scalability and routing result optimality. Specifically, the current traffic prediction models are not suitable for large urban networks due to the incomplete information of traffic conditions. Besides, existing routing systems can only plan the routes based on the past traffic conditions and struggle to update the optimal route for vehicles in real-time. As a result, the actual route taken by vehicles is different from the ground-truth optimal path. Therefore, we propose a Just-In-Time Predictive Route Planning framework to tackle these two problems. Firstly, we propose a Travel Time Constrained Top- kn Shortest Path algorithm which pre-computes a set of candidate paths with several switch points. This empowers vehicles to continuously have the opportunity to switch to better paths taking into account real-time traffic condition changes. Moreover, we present a query-driven prediction paradigm with ellipse-based searching space estimation, along with an efficient multi-queries handling mechanism. This not only allows for targeted traffic prediction by prioritizing regions with valuable yet outdated traffic information, but also provides optimal results for multiple queries based on real-time traffic evolution. Evaluations on two real-life road networks demonstrate the effectiveness and efficiency of our framework and methods.<br /> |confname =ICDE'24<br /> |link = https://ieeexplore.ieee.org/document/10598147/authors#authors<br /> |title= A Just-In-Time Framework for Continuous Routing<br /> |speaker=Zhenguo<br /> |date=2024-11-8<br /> }}<br /> {{Hist_seminar<br /> |abstract = Many networking tasks now employ deep learning (DL) to solve complex prediction and optimization problems. However, current design philosophy of DL-based algorithms entails intensive engineering overhead due to the manual design of deep neural networks (DNNs) for different networking tasks. Besides, DNNs tend to achieve poor generalization performance on unseen data distributions/environments. Motivated by the recent success of large language models (LLMs), this work studies the LLM adaptation for networking to explore a more sustainable design philosophy. With the powerful pre-trained knowledge, the LLM is promising to serve as the foundation model to achieve &quot;one model for all tasks&quot; with even better performance and stronger generalization. In pursuit of this vision, we present NetLLM, the first framework that provides a coherent design to harness the powerful capabilities of LLMs with low efforts to solve networking problems. Specifically, NetLLM empowers the LLM to effectively process multimodal data in networking and efficiently generate task-specific answers. Besides, NetLLM drastically reduces the costs of fine-tuning the LLM to acquire domain knowledge for networking. Across three networking-related use cases - viewport prediction, adaptive bitrate streaming and cluster job scheduling, we showcase that the NetLLM-adapted LLM significantly outperforms state-of-the-art algorithms.<br /> |confname =SIGCOMM'24<br /> |link = https://dl.acm.org/doi/abs/10.1145/3651890.3672268<br /> |title= NetLLM: Adapting Large Language Models for Networking<br /> |speaker=Yinghao<br /> |date=2024-11-8<br /> }}<br /> {{Hist_seminar<br /> |abstract = Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing two dedicated schedules for placing communication tasks. The proposed schedules eliminate redundant computations and communications and enable overlaps between intra-node and inter-node communications, ultimately reducing the overall training time. As the two schedules are not mutually exclusive, we provide comprehensive theoretical analyses and derive an automatic and accurate solution to determine which schedule should be applied in different scenarios. Experimental results on an 8-GPU server and a 32-GPU cluster demonstrate that Parm outperforms the state-of-the-art MoE training system, DeepSpeed-MoE, achieving 1.13× to 5.77× speedup on 1296 manually configured MoE layers and approximately 3× improvement on two real-world MoE models based on BERT and GPT-2.<br /> |confname =INFOCOM'24<br /> |link = https://ieeexplore.ieee.org/abstract/document/10621327<br /> |title= Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules<br /> |speaker=Mengqi<br /> |date=2024-11-1<br /> }}<br /> {{Hist_seminar<br /> |abstract = HD map is a key enabling technology towards fully autonomous driving. We propose VI-Map, the first system that leverages roadside infrastructure to enhance real-time HD mapping for autonomous driving. The core concept of VI-Map is to exploit the unique cumulative observations made by roadside infrastructure to build and maintain an accurate and current HD map. This HD map is then fused with on-vehicle HD maps in real time, resulting in a more comprehensive and up-to-date HD map. By extracting concise bird-eye-view features from infrastructure observations and utilizing vectorized map representations, VI-Map incurs low compute and communication overhead. We conducted end-to-end evaluations of VI-Map on a real-world testbed and a simulator. Experiment results show that VI-Map can construct decentimeter-level (up to 0.3 m) HD maps and achieve real-time (up to a delay of 42 ms) map fusion between driving vehicles and roadside infrastructure. This represents a significant improvement of 2.8× and 3× in map accuracy and coverage compared to the state-of-the-art online HD mapping approaches. A video demo of VI-Map on our real-world testbed is available at https://youtu.be/p2RO65R5Ezg.<br /> |confname=Mobicom'23<br /> |link = https://dl.acm.org/doi/abs/10.1145/3570361.3613280<br /> |title= VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous Driving<br /> |speaker=Wangyang<br /> |date=2024-11-1<br /> }}<br /> {{Hist_seminar<br /> |abstract = Video super-resolution (VSR) on mobile devices aims to restore high-resolution frames from their low-resolution counterparts, satisfying the requirements of performance, FLOPs and latency. On one hand, partial feature processing, as a classic and acknowledged strategy, is developed in current studies to reach an appropriate trade-off between FLOPs and accuracy. However, the splitting of partial feature processing strategy are usually performed in a blind manner, thereby reducing the computational efficiency and performance gains. On the other hand, current methods for mobile platforms primarily treat VSR as an extension of single-image super-resolution to reduce model calculation and inference latency. However, lacking inter-frame information interaction in current methods results in a suboptimal latency and accuracy trade-off. To this end, we propose a novel architecture, termed Feature Aggregating Network with Inter-frame Interaction (FANI), a lightweight yet considering frame-wise correlation VSR network, which could achieve real-time inference while maintaining superior performance. Our FANI accepts adjacent multi-frame low-resolution images as input and generally consists of several fully-connection-embedded modules, i.e., Multi-stage Partial Feature Distillation (MPFD) for capturing multi-level feature representations. Moreover, considering the importance of inter-frame alignment, we further employ a tiny Attention-based Frame Alignment (AFA) module to promote inter-frame information flow and aggregation efficiently. Extensive experiments on the well-known dataset and real-world mobile device demonstrate the superiority of our proposed FANI, which means that our FANI could be well adapted to mobile devices and produce visually pleasing results.<br /> |confname = ICDM'23<br /> |link = https://ieeexplore.ieee.org/abstract/document/10415812<br /> |title= Feature Aggregating Network with Inter-Frame Interaction for Efficient Video Super-Resolution<br /> |speaker=Shuhong<br /> |date=2024-10-25<br /> }}<br /> {{Hist_seminar<br /> |abstract = The proliferation of edge devices has pushed computing from the cloud to the data sources, and video analytics is among the most promising applications of edge computing. Running video analytics is compute- and latency-sensitive, as video frames are analyzed by complex deep neural networks (DNNs) which put severe pressure on resource-constrained edge devices. To resolve the tension between inference latency and resource cost, we present Polly, a cross-camera inference system that enables co-located cameras with different but overlapping fields of views (FoVs) to share inference results between one another, thus eliminating the redundant inference work for objects in the same physical area. Polly’s design solves two basic challenges of cross-camera inference: how to identify overlapping FoVs automatically, and how to share inference results accurately across cameras. Evaluation on NVIDIA Jetson Nano with a real-world traffic surveillance dataset shows that Polly reduces the inference latency by up to 71.4% while achieving almost the same detection accuracy with state-of-the-art systems.<br /> |confname= INFOCOM'23<br /> |link = https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10229045<br /> |title= Cross-Camera Inference on the Constrained Edge<br /> |speaker=Xinyan<br /> |date=2024-10-25<br /> }}<br /> {{Hist_seminar<br /> |abstract = Smart cameras with on-device deep learning inference capabilities are enabling distributed video analytics at the data source without sending raw video data over the often unreliable and congested wireless network. However, how to unleash the full potential of the computing power of the camera network requires careful coordination among the distributed cameras, catering to the uneven workload distribution and the heterogeneous computing capabilities. This paper presents CrossVision, a distributed framework for real-time video analytics, that retains all video data on cameras while achieving low inference delay and high inference accuracy. The key idea behind CrossVision is that there is a significant information redundancy in the video content captured by cameras with overlapped Field-of-Views (FoVs), which can be exploited to reduce inference workload as well as improve inference accuracy between correlated cameras. CrossVision consists of three main components to realize its function: a Region-of-Interest (RoI) Matcher that discovers video content correlation based on a segmented FoV transformation scheme; a Workload Balancer that implements a randomized workload balancing strategy based on a bulk-queuing analysis, taking into account the cameras’ predicted future workload arrivals; an Accuracy Guard that ensures that the inference accuracy is not sacrificed as redundant information is discarded. We evaluate CrossVision in a hardware-augmented simulator and on real-world cross-camera datasets, and the results show that CrossVision is able to significantly reduce inference delay while improving the inference accuracy compared to a variety of baseline approaches.<br /> |confname= TMC'24<br /> |link = https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10202594<br /> |title= CrossVision: Real-Time On-Camera Video Analysis via Common RoI Load Balancing<br /> |speaker=Xinyan<br /> |date=2024-10-25<br /> }}<br /> {{Hist_seminar<br /> |abstract = LoRa is a promising technology that offers ubiquitous low-power IoT connectivity. With the features of multi-channel communication, orthogonal transmission, and spectrum sharing, LoRaWAN is poised to connect millions of IoT devices across thousands of logical channels. However, current LoRa gateways utilize hardwired Rx chains that cover only a small fraction (&lt;1%) of the logical channels, limiting the potential for massive LoRa communications. This paper presents XGate, a novel gateway design that uses a single Rx chain to concurrently receive packets from all logical channels, fundamentally enabling scalable LoRa transmission and flexible network access. Unlike hardwired Rx chains in the current gateway design, XGate allocates resources including software-controlled Rx chains and demodulators based on the extracted meta information of incoming packets. XGate addresses a series of challenges to efficiently detect incoming packets without prior knowledge of their parameter configurations. Evaluations show that XGate boosts LoRa concurrent transmissions by 8.4× than state-of-the-art.<br /> |confname=Mobicom' 24<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3636534.3649375<br /> |title= Revolutionizing LoRa Gateway with XGate: Scalable Concurrent Transmission across Massive Logical Channels<br /> |speaker=Chenkai<br /> |date=2024-10-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Deep learning training (DLT), e.g., large language model (LLM) training, has become one of the most important services in multitenant cloud computing. By deeply studying in-production DLT jobs, we observed that communication contention among different DLT jobs seriously influences the overall GPU computation utilization, resulting in the low efficiency of the training cluster. In this paper, we present Crux, a communication scheduler that aims to maximize GPU computation utilization by mitigating the communication contention among DLT jobs. Maximizing GPU computation utilization for DLT, nevertheless, is NP-Complete; thus, we formulate and prove a novel theorem to approach this goal by GPU intensity-aware communication scheduling. Then, we propose an approach that prioritizes the DLT flows with high GPU computation intensity, reducing potential communication contention. Our 96-GPU testbed experiments show that Crux improves 8.3% to 14.8% GPU computation utilization. The large-scale production trace-based simulation further shows that Crux increases GPU computation utilization by up to 23% compared with alternatives including Sincronia, TACCL, and CASSINI.<br /> |confname=SIGCOMM' 24<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3651890.3672239<br /> |title= Crux: GPU-Efficient Communication Scheduling for Deep Learning Training<br /> |speaker=Youwei<br /> |date=2024-10-18<br /> }}<br /> {{Hist_seminar<br /> |abstract = Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the locomotion part, most works still depend on map-based planning approaches. The gap between RGB space and map space makes it difficult to directly transfer the knowledge from foundation models to navigation tasks. In this work, we propose a Pixel-guided Navigation skill (PixNav), which bridges the gap between the foundation models and the embodied navigation task. It is straightforward for recent foundation models to indicate an object by pixels, and with pixels as the goal specification, our method becomes a versatile navigation policy towards all different kinds of objects. Besides, our PixNav is a pure RGB-based policy that can reduce the cost of homeassistance robots. Experiments demonstrate the robustness of the PixNav which achieves 80+% success rate in the local path-planning task. To perform long-horizon object navigation, we design an LLM-based planner to utilize the commonsense knowledge between objects and rooms to select the best waypoint. Evaluations across both photorealistic indoor simulators and real-world environments validate the effectiveness of our proposed navigation strategy.<br /> |confname=ICRA' 24<br /> |link = https://ieeexplore.ieee.org/document/10610499<br /> |title= Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill<br /> |speaker=Qinyong<br /> |date=2024-10-11<br /> }}<br /> {{Hist_seminar<br /> |abstract = Datacenter networks today provide best-effort delivery—messages may observe unpredictable queueing, delays, and drops due to switch buffer overflows within the network. Such weak guarantees reduce the set of assumptions that system designers can rely upon from the network, thus introducing inefficiency and complexity in host hardware and software. We present Harmony, a datacenter network architecture that provides powerful &quot;congestion-free&quot; message delivery guarantees—each message, once transmitted by the sender, observes bounded queueing at each switch in the network. Thus, network delays are bounded in failure-free scenarios, and congestion-related drops are completely eliminated. We establish, both theoretically and empirically, that Harmony provides such powerful guarantees with near-zero overheads compared to best-effort delivery networks: it incurs a tiny additive latency overhead that diminishes with message sizes, while achieving near-optimal network utilization.<br /> |confname=NSDI' 24<br /> |link = https://www.usenix.org/conference/nsdi24/presentation/agarwal-saksham<br /> |title= Harmony: A Congestion-free Datacenter Architecture<br /> |speaker=Junzhe<br /> |date=2024-10-11<br /> }}<br /> {{Hist_seminar<br /> |abstract = Overlapping cameras offer exciting opportunities to view a scene from different angles, allowing for more advanced, comprehensive and robust analysis. However, existing video analytics systems for multi-camera streams are mostly limited to (i) per-camera processing and aggregation and (ii) workload-agnostic centralized processing architectures. In this paper, we present Argus, a distributed video analytics system with cross-camera collaboration on smart cameras. We identify multi-camera, multi-target tracking as the primary task of multi-camera video analytics and develop a novel technique that avoids redundant, processing-heavy identification tasks by leveraging object-wise spatio-temporal association in the overlapping fields of view across multiple cameras. We further develop a set of techniques to perform these operations across distributed cameras without cloud support at low latency by (i) dynamically ordering the camera and object inspection sequence and (ii) flexibly distributing the workload across smart cameras, taking into account network transmission and heterogeneous computational capacities. Evaluation of three real-world overlapping camera datasets with two Nvidia Jetson devices shows that Argus reduces the number of object identifications and end-to-end latency by up to 7.13× and 2.19× (4.86× and 1.60× compared to the state-of-the-art), while achieving comparable tracking quality.<br /> |confname=TMC' 24<br /> |link = https://ieeexplore.ieee.org/abstract/document/10682605<br /> |title= Argus: Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart Cameras<br /> |speaker=Bairong<br /> |date=2024-9-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = We present FarfetchFusion, a fully mobile live 3D telepresence system. Enabling mobile live telepresence is a challenging problem as it requires i) realistic reconstruction of the user and ii) high responsiveness for immersive experience. We first thoroughly analyze the live 3D telepresence pipeline and identify three critical challenges: i) 3D data streaming latency and compression complexity, ii) computational complexity of volumetric fusion-based 3D reconstruction, and iii) inconsistent reconstruction quality due to sparsity of mobile 3D sensors. To tackle the challenges, we propose a disentangled fusion approach, which separates invariant regions and dynamically changing regions with our low-complexity spatio-temporal alignment technique, topology anchoring. We then design and implement an end-to-end system, which achieves realistic reconstruction quality comparable to existing server-based solutions while meeting the real-time performance requirements (&lt;100 ms end-to-end latency, 30 fps throughput, &lt;16 ms motion-to-photon latency) solely relying on mobile computation capability.<br /> |confname=MobiCom' 23<br /> |link = https://dl.acm.org/doi/abs/10.1145/3570361.3592525<br /> |title= FarfetchFusion: Towards Fully Mobile Live 3D Telepresence Platform<br /> |speaker=Mengfan<br /> |date=2024-9-29<br /> }}<br /> {{Hist_seminar<br /> |abstract = Increasing bandwidth demands of mobile video streaming pose a challenge in optimizing the Quality of Experience (QoE) for better user engagement. Multipath transmission promises to extend network capacity by utilizing multiple wireless links simultaneously. Previous studies mainly tune the packet scheduler in multipath transmission, expecting higher QoE by accelerating transmission. However, since Adaptive BitRate (ABR) algorithms overlook the impact of multipath scheduling on throughput prediction, multipath adaptive streaming can even experience lower QoE than single-path. This paper proposes Chorus, a cross-layer framework that coordinates multipath scheduling with adaptive streaming to optimize QoE jointly. Chorus establishes two-way feedback control loops between the server and the client. Furthermore, Chorus introduces Coarse-grained Decisions, which assist appropriate bitrate selection by considering the scheduling decision in throughput prediction, and Finegrained Corrections, which meet the predicted throughput by QoE-oriented multipath scheduling. Extensive emulation and real-world mobile Internet evaluations show that Chorus outperforms the state-of-the-art MPQUIC scheduler, improving average QoE by 23.5% and 65.7%, respectively. <br /> |confname=MobiCom' 24<br /> |link = https://dl.acm.org/doi/pdf/10.1145/3636534.3649359<br /> |title= Chorus: Coordinating Mobile Multipath Scheduling and Adaptive Video Streaming<br /> |speaker=Jiahao<br /> |date=2024-9-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = In Distributed Quantum Computing (DQC), quantum bits (qubits) used in a quantum circuit may be distributed on multiple Quantum Computers (QCs) connected by a Quantum Data Network (QDN). To perform a quantum gate operation involving two qubits on different QCs, we have to establish an Entanglement Connection (EC) between their host QCs. Existing EC establishment schemes result in a long EC establishment time, and low quantum resource utilization.In this paper, we propose an Asynchronous Entanglement Routing and Provisioning (AEPR) scheme to minimize the task completion time in DQC systems. AEPR has three distinct features: (i). Entanglement Paths (EPs) for a given SD pair are predetermined to eliminate the need for runtime calculation; (ii). Entanglement Links (ELs) are created proactively to reduce the time needed create EL on demand; and (iii). For a given EC request, quantum swapping along an EP is performed by a repeater whenever two adjacent ELs are created, so precious quantum resources at the repeater can be released immediately thereafter for other ELs and ECs. Extensive simulations show that AEPR can save up to 76.05% of the average task completion time in DQC systems compared with the state-of-the-art entanglement routing schemes designed to maximize QDN throughput. <br /> |confname=INFOCOM' 23<br /> |link = https://doi.org/10.1109/infocom53939.2023.10229101<br /> |title= Asynchronous Entanglement Provisioning and Routing for Distributed Quantum Computing<br /> |speaker=Yaliang<br /> |date=2024-9-13<br /> }}<br /> {{Hist_seminar<br /> |abstract = Recent advances in network and mobile computing. <br /> |confname=Talk<br /> |link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2024<br /> |title=[[Resource:Paper_Carnival_2024|Paper Carnival 2024]]<br /> |speaker=All<br /> |date=2024-9-5 ~ 2024-9-6<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10355583<br /> |title=Hi2LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost<br /> |speaker=Jiyi<br /> |date=2024-07-05}}<br /> {{Hist_seminar<br /> |confname=ICRA'23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10160341<br /> |title=D2CoPlan: A Differentiable Decentralized Planner for Multi-Robot Coverage<br /> |speaker=Xianyang<br /> |date=2024-07-05}}<br /> {{Hist_seminar<br /> |confname=TMC'24<br /> |link=https://ieeexplore.ieee.org/abstract/document/10440565<br /> |title=Joint Deployment of Truck-drone Systems for Camera-based Object Monitoring<br /> |speaker=Luwei<br /> |date=2024-06-28}}<br /> {{Hist_seminar<br /> |confname=NSDI'23<br /> |link=https://www.usenix.org/conference/nsdi23/presentation/li-zhuqi<br /> |title=Dashlet: Taming Swipe Uncertainty for Robust Short Video Streaming<br /> |speaker=Mengqi<br /> |date=2024-06-28}}<br /> {{Hist_seminar<br /> |confname=MobiCom'23<br /> |link=https://arxiv.org/pdf/2308.06053<br /> |title=Cost-effective On-device Continual Learning over Memory Hierarchy with Miro<br /> |speaker=Jiale<br /> |date=2024-06-14}}<br /> {{Hist_seminar<br /> |confname=SEC'23<br /> |link=https://www.cs.hunter.cuny.edu/~sdebroy/publication-files/SEC2023_CR.pdf<br /> |title=On Balancing Latency and Quality of Edge-Native Multi-View 3D Reconstruction<br /> |speaker=Yang Wang<br /> |date=2024-06-14}}<br /> {{Hist_seminar<br /> |confname=MobiSys'21<br /> |link=https://dl.acm.org/doi/10.1145/3458864.3466867<br /> |title=RayTrack: enabling interference-free outdoor mobile VLC with dynamic field-of-view<br /> |speaker=Mengyu<br /> |date=2024-06-07}}<br /> {{Hist_seminar<br /> |confname=MM'23<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3581783.3613907<br /> |title=Hermes: Leveraging Implicit Inter-Frame Correlation for Bandwidth-Efficient Mobile Volumetric Video Streaming<br /> |speaker=Mengfan<br /> |date=2024-06-07}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3603269.3604853<br /> |title=Masking Corruption Packet Losses in Datacenter Networks with Link-local Retransmission<br /> |speaker=Jiacheng<br /> |date=2024-05-31}}<br /> {{Hist_seminar<br /> |confname=FAST '23<br /> |link=https://www.usenix.org/system/files/fast23-li-pengfei.pdf<br /> |title=ROLEX: A Scalable RDMA-oriented Learned Key-Value Store for Disaggregated Memory Systems<br /> |speaker=Haotian<br /> |date=2024-05-31}}<br /> {{Hist_seminar<br /> |confname=ICRA 2023<br /> |link=https://ieeexplore.ieee.org/document/10161345<br /> |title=Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistants<br /> |speaker=Zhenhua<br /> |date=2024-05-24}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://xplorestaging.ieee.org/document/10229025<br /> |title=RecMon: A Deep Learning-based Data Recovery System for Network Monitoring<br /> |speaker=Zhenguo<br /> |date=2024-05-24}}<br /> {{Hist_seminar<br /> |confname=IPSN 2023<br /> |link=https://dl.acm.org/doi/10.1145/3583120.3586963<br /> |title=FLoRa: Energy-Efficient, Reliable, and Beamforming-Assisted Over-The-Air Firmware Update in LoRa Networks<br /> |speaker=Kai Chen<br /> |date=2024-05-10}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/abstract/document/10228941/<br /> |title=Prophet: An Efficient Feature Indexing Mechanism for Similarity Data Sharing at Network Edge<br /> |speaker=Rong Cong<br /> |date=2024-05-10}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM 2020<br /> |link=https://dl.acm.org/doi/10.1145/3387514.3405853<br /> |title=Concurrent Entanglement Routing for Quantum Networks: Model and Designs<br /> |speaker=Yaliang<br /> |date=2024-04-28}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2023<br /> |link=https://dl.acm.org/doi/10.1145/3570361.3592523<br /> |title=NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras<br /> |speaker=Jiyi<br /> |date=2024-04-12}}<br /> {{Hist_seminar<br /> |confname=Neurips 2017<br /> |link=https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf<br /> |title=Attention Is All You Need<br /> |speaker=Qinyong<br /> |date=2024-04-12}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/document/10229104<br /> |title=Achieving Resilient and Performance-Guaranteed Routing in Space-Terrestrial Integrated Networks<br /> |speaker=Luwei<br /> |date=2024-03-29}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/document/10229043<br /> |title=Communication-aware DNN pruning<br /> |speaker=Shuhong<br /> |date=2024-03-29}}<br /> {{Hist_seminar<br /> |confname=IROS 2021<br /> |link=https://ieeexplore.ieee.org/abstract/document/9636344<br /> |title=Scalable Reinforcement Learning Policies for Multi-Agent Control<br /> |speaker=Xianyang<br /> |date=2024-03-22}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/document/10228936/<br /> |title=Breaking the Throughput Limit of LED-Camera Communication via Superposed Polarization<br /> |speaker=Mengyu<br /> |date=2024-03-22}}<br /> {{Hist_seminar<br /> |confname=MobiHoc '23<br /> |link=https://dl.acm.org/doi/10.1145/3565287.3610254<br /> |title=SRLoRa: Neural-enhanced LoRa Weak Signal Decoding with Multi-gateway Super Resolution<br /> |speaker=Pengfei<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=TMC '23<br /> |link=https://ieeexplore.ieee.org/document/9839387<br /> |title=Integrated Sensing and Communication in UAV Swarms for Cooperative Multiple Targets Tracking<br /> |speaker=Kun Wang<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/10.1145/3570361.3592496<br /> |title=Towards Spatial Selection Transmission for Low-end IoT devices with SpotSound<br /> |speaker=Jiajun<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=NSDI '23<br /> |link=https://www.usenix.org/conference/nsdi23/presentation/padmanabhan<br /> |title=Gemel: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge<br /> |speaker=Mengqi<br /> |date=2024-01-18}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/10.1145/3570361.3592514<br /> |title=Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios<br /> |speaker=Yang Wang<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10228884<br /> |title=DisProTrack: Distributed Provenance Tracking over Serverless Applications<br /> |speaker=Xinyu<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=MobiSys '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3581791.3596855<br /> |title=When VLC Meets Under-Screen Camera<br /> |speaker=Jiacheng<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3570361.3592530<br /> |title=MetaStream: Live Volumetric Content Capture, Creation, Delivery, and Rendering in Real Time<br /> |speaker=Jiale<br /> |date=2024-01-11}}<br /> {{Hist_seminar<br /> |confname=ToSN '23<br /> |link=https://dl.acm.org/doi/10.1145/3571586<br /> |title=Decoding LoRa Collisions via Parallel Alignment<br /> |speaker=Kai Chen<br /> |date=2024-01-04}}<br /> {{Hist_seminar<br /> |confname=MASS '23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10298524<br /> |title=WiMix: A Lightweight Multimodal Human Activity Recognition System based on WiFi and Vision<br /> |speaker=Haotian<br /> |date=2024-01-04}}<br /> {{Hist_seminar<br /> |confname=TMC '23<br /> |link=https://ieeexplore.ieee.org/document/9888056<br /> |title=A Multicriteria-Based Forwarding Strategy for Interest Flooding Mitigation on Named Data Wireless Networking<br /> |speaker=Zhenghua<br /> |date=2024-01-04}}<br /> <br /> ====2023====<br /> {{Hist_seminar<br /> |confname=SenSys' 22<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568547<br /> |title=LLDPC: A Low-Density Parity-Check Coding Scheme for LoRa Networks<br /> |speaker=Wengliang<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=ToN' 22<br /> |link=https://ieeexplore.ieee.org/document/9690589/<br /> |title=Continuous Network Update With Consistency Guaranteed in Software-Defined Networks<br /> |speaker=Yaliang<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/document/10229105<br /> |title=OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos<br /> |speaker=Mengfan<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3603269.3604849<br /> |title=Network Load Balancing with In-network Reordering Support for RDMA<br /> |speaker=Jiyi<br /> |date=2023-12-21}}<br /> {{Hist_seminar<br /> |confname=TMC '22<br /> |link=https://ieeexplore.ieee.org/abstract/document/10209220<br /> |title=F3VeTrac: Enabling Fine-grained, Fully-road-covered, and Fully-individual penetrative Vehicle Trajectory Recovery<br /> |speaker=Zhenguo<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3603269.3604819<br /> |title=ZGaming: Zero-Latency 3D Cloud Gaming by Image Prediction<br /> |speaker=Wenjie<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=NeurIPS '20<br /> |link=https://arxiv.org/abs/2010.13110<br /> |title=Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks<br /> |speaker=Jiahui<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3570361.3592522<br /> |title=CoreKube: An Efficient, Autoscaling and Resilient Mobile Core System<br /> |speaker=Qinyong<br /> |date=2023-12-07}}<br /> {{Hist_seminar<br /> |confname=TMC '20<br /> |link=https://ieeexplore.ieee.org/document/8708935<br /> |title=SmartVLC: Co-Designing Smart Lighting and Communication for Visible Light Networks<br /> |speaker=Mengyu<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=TMC '23<br /> |link=https://ieeexplore.ieee.org/document/9566795<br /> |title=A Fast, Reliable, Opportunistic Broadcast Scheme With Mitigation of Internal Interference in VANETs<br /> |speaker=Luwei<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/document/10228990<br /> |title=ResMap: Exploiting Sparse Residual Feature Map for Accelerating Cross-Edge Video Analytics<br /> |speaker=Xianyang<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=NSDI '23<br /> |link=https://www.usenix.org/conference/nsdi23/presentation/yu<br /> |title=Following the Data, Not the Function: Rethinking Function Orchestration in Serverless Computing<br /> |speaker=Mengfan<br /> |date=2023-11-16}}<br /> {{Hist_seminar<br /> |confname=ASPLOS '23<br /> |link=https://dl.acm.org/doi/10.1145/3582016.3582050<br /> |title=LEGO: Empowering Chip-Level Functionality Plug-and-Play for Next-Generation IoT Devices<br /> |speaker=Pengfei<br /> |date=2023-11-09}}<br /> {{Hist_seminar<br /> |confname=IoTJ '23<br /> |link=https://ieeexplore.ieee.org/document/9714482?denied=<br /> |title=Hierarchical Aerial Computing for Internet of Things via Cooperation of HAPs and UAVs<br /> |speaker=Kun Wang<br /> |date=2023-11-09}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/abstract/document/10229089<br /> |title=Search in the Expanse: Towards Active and Global IPv6 Hitlists<br /> |speaker=Xinyu<br /> |date=2023-11-2}}<br /> {{Hist_seminar<br /> |confname=IPSN '23<br /> |link=https://dl.acm.org/doi/10.1145/3583120.3586969<br /> |title=Link Quality Modeling for LoRa Networks in Orchards<br /> |speaker=Jiacheng<br /> |date=2023-11-02}}<br /> {{Hist_seminar<br /> |confname=INFOCOM '23<br /> |link=https://ieeexplore.ieee.org/document/10228896<br /> |title=Rebuffering but not Suffering: Exploring Continuous-Time Quantitative QoE by User’s Exiting Behaviors<br /> |speaker=Jiajun<br /> |date=2023-11-02}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://yuanmu97.github.io/preprint/packetgame_sigcomm23.pdf<br /> |title=PacketGame: Multi-Stream Packet Gating for Concurrent Video Inference at Scale<br /> |speaker=Shuhong<br /> |date=2023-11-02}}<br /> {{Hist_seminar<br /> |confname=MobiCom '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3570361.3613271<br /> |title=Robust Real-time Multi-vehicle Collaboration on Asynchronous Sensors<br /> |speaker=Yang Wang<br /> |date=2023-10-26}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3603269.3604816<br /> |title=Ditto: Efficient Serverless Analytics with Elastic Parallelism<br /> |speaker=Mengqi Ma<br /> |date=2023-10-26}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '23<br /> |link=https://dl.acm.org/doi/10.1145/3603269.3604832<br /> |title=CellFusion: Multipath Vehicle-to-Cloud Video Streaming with Network Coding in the Wild<br /> |speaker=Rong Cong<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |confname=SigMetrics '23<br /> |link=https://dl.acm.org/doi/abs/10.1145/3579445<br /> |title=DaeMon: Architectural Support for Efficient Data Movement in Fully Disaggregated Systems<br /> |speaker=Jiyi<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |confname=SenSys '22<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568533<br /> |title=MaLoRaGW: Multi-User MIMO Transmission for LoRa<br /> |speaker=Kai Chen<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |confname=SIGCOMM '22<br /> |link=https://dl.acm.org/doi/10.1145/3544216.3544244<br /> |title=Software-defined network assimilation: bridging the last mile towards centralized network configuration management with NAssim<br /> |speaker=Yaliang<br /> |date=2023-10-08}}<br /> {{Hist_seminar<br /> |abstract = Recent advances in network and mobile computing. <br /> |confname=Talk<br /> |link=[Resource:Paper Carnival 2023|Paper Carnival 2023<br /> |title=]<br /> |speaker=All<br /> |date=2023-9-20<br /> }}<br /> {{Hist_seminar<br /> |abstract=Realizing Digital Twins for Vehicular Networks: Towards Future Network Evolution<br /> |confname=Tech. Talk<br /> |link=#<br /> |title=Trustworthy AI<br /> |speaker=Prof. Zhibo Wang<br /> |date=2023-07-11}}<br /> {{Hist_seminar<br /> |abstract=Realizing Digital Twins for Vehicular Networks: Towards Future Network Evolution<br /> |confname=submission<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=XX Towards Future Network Evolution<br /> |speaker=Zhenguo<br /> |date=2023-06-08}}<br /> {{Hist_seminar<br /> |abstract=Realizing Digital Twins for Vehicular Networks: Towards Future Network Evolution<br /> |confname=Tech. Talk<br /> |link=#<br /> |title=Rechargeable network<br /> |speaker=Prof. Tang Liu<br /> |date=2023-06-15}}<br /> {{Hist_seminar<br /> |abstract = Gondola<br /> |confname=SEC 2023<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Gondola: A Comprehensive Simulator for OEC<br /> |speaker=Qinyong<br /> |date=2023-06-08}}<br /> {{Hist_seminar<br /> |abstract=CHL<br /> |confname=INFOCOM 2024<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=CHL<br /> |speaker=Wenliang<br /> |date=2023-06-01}}<br /> {{Hist_seminar<br /> |abstract = EdgeLight<br /> |confname=SEC 2023<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=EdgeLight<br /> |speaker=Xianyang<br /> |date=2023-06-01}}<br /> {{Hist_seminar<br /> |confname=Sensys 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568527<br /> |title=Enhancing Video Analytics Accuracy via Real-time Automated Camera Parameter Tuning<br /> |speaker=Silence<br /> |date=2023-05-25}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://arxiv.org/pdf/2301.06363<br /> |title=A2-UAV: Application-Aware Content and Network Optimization of Edge-Assisted UAV Systems<br /> |speaker=Jiahui<br /> |date=2023-05-25}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9519523<br /> |title=Quick and Reliable LoRa Physical-layer Data Aggregation through Multi-Packet Reception<br /> |speaker=Kaiwen<br /> |date=2023-05-11}}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3560517<br /> |title=MobiDepth: real-time depth estimation using on-device dual cameras<br /> |speaker=Wenjie<br /> |date=2023-05-11}}<br /> {{Hist_seminar<br /> |confname=SEC 2022<br /> |link=https://ieeexplore.ieee.org/abstract/document/9996714<br /> |title=ENTS: An Edge-native Task Scheduling System for Collaborative Edge Computing<br /> |speaker=Qinyong<br /> |date=2023-05-11}}<br /> {{Hist_seminar<br /> |confname=TMC 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9519523<br /> |title=An Efficient Cooperative Transmission Based Opportunistic Broadcast Scheme in VANETs<br /> |speaker=Luwei<br /> |date=2023-05-04}}<br /> {{Hist_seminar<br /> |confname=CVPR 2022<br /> |link=https://arxiv.org/pdf/2203.09249.pdf<br /> |title=Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning<br /> |speaker=Jiaqi<br /> |date=2023-05-04}}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8978742<br /> |title=Pushing the Data Rate of Practical VLC via Combinatorial Light Emission<br /> |speaker=Mengyu<br /> |date=2023-05-04}}<br /> {{Hist_seminar<br /> |confname=SenSys 2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3384419.3430898<br /> |title=Deep compressive offloading: speeding up neural network inference by trading edge computation for network latency<br /> |speaker=Crong<br /> |date=2023-04-27}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9796804<br /> |title=DBAC: Directory-Based Access Control for Geographically Distributed IoT Systems<br /> |speaker=Xinyu<br /> |date=2023-04-27}}<br /> {{Hist_seminar<br /> |confname=SenSys 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3560905.3568501<br /> |title=Turbo: Opportunistic Enhancement for Edge Video Analytics<br /> |speaker=Jiajun<br /> |date=2023-04-27}}<br /> {{Hist_seminar<br /> |confname=IPSN 2023<br /> |link=https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/602741/ipsn23-22.pdf?sequence=1&amp;isAllowed=y<br /> |title=Hydra: Concurrent Coordination for Fault-tolerant Networking<br /> |date=2023-04-20<br /> |speaker=Pengfei}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3517021<br /> |title=Experience: practical indoor localization for malls<br /> |date=2023-04-20<br /> |speaker=Zhuoliu}}<br /> {{Hist_seminar<br /> |confname=IWQoS 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9796680<br /> |title=Geographic Low-Earth-Orbit Networking without QoS Bottlenecks from Infrastructure Mobility<br /> |date=2023-04-20<br /> |speaker=Kun}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2023<br /> |link=https://www.jianguoyun.com/p/DaSn-A0Q_LXjBxjS9f8EIAA<br /> |title=Push the Limit of LPWANs with Concurrent Transmissions<br /> |date=2023-04-06<br /> |speaker=Wenliang}}<br /> {{Hist_seminar<br /> |confname=TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9942345<br /> |title=MOTO: Mobility-Aware Online Task Offloading with Adaptive Load Balancing in Small-Cell MEC<br /> |date=2023-04-06<br /> |speaker=Xianyang}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9796680<br /> |title=MoDEMS: Optimizing Edge Computing Migrations For User Mobility<br /> |date=2023-04-06<br /> |speaker=Zhenguo}}<br /> {{Hist_seminar<br /> |confname=IEEE Photonics Journal 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=10028767<br /> |title=Physical-Layer Network Coding Enhanced Visible Light Communications Using RGB LEDs <br /> |date=2023-03-23<br /> |speaker=Jiahui}}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3498361.3539765<br /> |title=Tutti: coupling 5G RAN and mobile edge computing for latency-critical video analytics<br /> |date=2023-03-23<br /> |speaker=Silience}}<br /> {{Hist_seminar<br /> |confname=ACM Computing Surveys 2005<br /> |link=https://dl.acm.org/doi/10.1145/1118890.1118892<br /> |title=When and How to Develop Domain-Specific Languages<br /> |date=2023-03-23<br /> |speaker=Shu}}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3560544<br /> |title=BSMA: Scalable LoRa networks using full duplex gateways <br /> |date=2023-02-13<br /> |speaker=Kaiwen}}<br /> {{Hist_seminar<br /> |confname=MobiSys 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3498361.3539765<br /> |title=Memory-efficient DNN Training on Mobile Devices<br /> |date=2023-02-13<br /> |speaker=Wenjie}}<br /> {{Hist_seminar<br /> |confname=SigMetrics 2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3530892<br /> |title=WiseFuse: Workload Characterization and DAG Transformation for Serverless Workflows <br /> |date=2023-02-13<br /> |speaker=Qinyong}}<br /> {{Hist_seminar<br /> |confname=Sensys2022<br /> |link=https://www4.comp.polyu.edu.hk/~csyqzheng/papers/HyLink-SenSys22.pdf<br /> |title=HyLink: Towards High Throughput LPWANs with LoRa Compatible Communication<br /> |date=2023-02-13<br /> |speaker=Mengyu}}<br /> {{Hist_seminar<br /> |confname=TMC 2023<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9451627<br /> |title=Multi-Task Allocation in Mobile Crowd SensingWith Mobility Prediction <br /> |date=2023-02-13<br /> |speaker=Zhenguo}}<br /> {{Hist_seminar<br /> |confname=TMC2022<br /> |link=https://ieeexplore.ieee.org/document/9410408/<br /> |title=FLORA: Fuzzy Based Load-Balanced Opportunistic Routing for Asynchronous Duty-Cycled WSNs<br /> |date=2023-02-06<br /> |speaker=Luwei}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2022<br /> |link=https://dl.acm.org/doi/abs/10.1145/3495243.3560551<br /> |title=Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI <br /> |date=2023-02-06<br /> |speaker=Crong}}<br /> {{Hist_seminar<br /> |confname=MobiSys 2022<br /> |link=https://dl.acm.org/doi/abs/10.1145/3498361.3538919<br /> |title=TinyNET: a lightweight, modular, and unified network architecture for the internet of things<br /> |date=2023-02-06<br /> |speaker=Xinyu}}<br /> <br /> ====2022====<br /> {{Hist_seminar<br /> |confname=Mobicom2022<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3495243.3567652<br /> |title=IoTree: a battery-free wearable system with biocompatible sensors for continuous tree health monitoring<br /> |date=2022-11-25<br /> |speaker=Pengfei}}<br /> {{Hist_seminar<br /> |confname=TMC2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9373980<br /> |title=An Online Framework for Joint Network Selection and Service Placement in Mobile Edge Computing<br /> |date=2022-11-25<br /> |speaker=Kun}}<br /> {{Hist_seminar<br /> |confname=Sensys 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3485730.3485938<br /> |title=RT-mDL: Supporting Real-Time Mixed Deep Learning Tasks on Edge Platforms<br /> |date=2022-11-25<br /> |speaker=Jiajun}}<br /> {{Hist_seminar<br /> |confname=ICNP2022<br /> |link=https://www.jianguoyun.com/p/DUT5aHYQ_LXjBxiBx-UEIAA<br /> |title=Ostinato: Combating LoRa Weak Links in Real Deployments<br /> |speaker=Wenliang<br /> |date=2022-11-08}}<br /> {{Hist_seminar<br /> |confname=TMC2022<br /> |link=https://eprints.gla.ac.uk/274277/1/274277.pdf<br /> |title=A Unified Framework for Joint Sensing and Communication in Resource Constrained Mobile Edge Networks<br /> |speaker=Xianyang<br /> |date=2022-11-08}}<br /> {{Hist_seminar<br /> |confname=CVPR 2022<br /> |link=https://openaccess.thecvf.com/content/CVPR2022/papers/Dong_Federated_Class-Incremental_Learning_CVPR_2022_paper.pdf<br /> |title=Federated Class-Incremental Learning<br /> |speaker=Jianqi<br /> |date=2022-11-08}}<br /> {{Hist_seminar<br /> |confname=MobiCom 2022<br /> |link=https://dl.acm.org/doi/abs/10.1145/3495243.3560551<br /> |title=Real-time neural network inference on extremely weak devices: agile offloading with explainable AI<br /> |speaker=Crong<br /> |date=2022-11-01<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://ieeexplore.ieee.org/document/9796711<br /> |title=An RFID and Computer Vision Fusion System for Book Inventory using Mobile Robot<br /> |speaker=Zhuoliu<br /> |date=2022-11-01<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3447993.3448631<br /> |title=One Tag, Two Codes: Identifying Optical Barcodes with NFC<br /> |date=2022-10-25<br /> |speaker=Jiangshu}}<br /> {{Hist_seminar<br /> |confname=IoTJ 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9444334<br /> |title=Service Coverage for Satellite Edge Computing<br /> |date=2022-10-25<br /> |speaker=Qinyong}}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2022<br /> |link=https://arxiv.org/pdf/2203.10470<br /> |title=EdgeMatrix: A Resources Redefined Edge-Cloud System for Prioritized Services<br /> |date=2022-10-25<br /> |speaker=Xinyu}}<br /> {{Hist_seminar<br /> |confname=ICNP 2022<br /> |link=https://www.jianguoyun.com/p/DXDTOyEQ_LXjBxiLjt8EIAA<br /> |title=CONST: Exploiting Spatial-Temporal Correlation for Multi-Gateway based Reliable LoRa Reception<br /> |speaker=Kaiwen<br /> |date=2022-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=Mobicom 2022<br /> |link=https://arxiv.org/pdf/2206.07509.pdf<br /> |title=Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading<br /> |speaker=Wenjie<br /> |date=2022-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9151371<br /> |title=Imitation Learning Enabled Task Scheduling for Online Vehicular Edge Computing<br /> |speaker=Zhenguo<br /> |date=2022-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3241539.3241543<br /> |title=ChromaCode: A Fully Imperceptible Screen-Camera Communication System<br /> |date=2022-10-10<br /> |speaker=Mengyu}}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9673682<br /> |title=MVPose:Realtime Multi-Person Pose Estimation using Motion Vector on Mobile Devices<br /> |date=2022-10-10<br /> |speaker=Silence}}<br /> {{Hist_seminar<br /> |confname=TMC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9352566<br /> |title=Optimizing Energy Consumption of Mobile Games<br /> |date=2022-10-10<br /> |speaker=Luwei}}<br /> {{Hist_seminar<br /> |abstract = Recent advances in network and mobile computing. <br /> |confname=talk<br /> |link=[Resource:Paper Carnival 2022|Paper Carnival 2022<br /> |title=]<br /> |speaker=all<br /> |date=2022-9-27<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488756<br /> |title=Resource-Efficient Federated Learning with Hierarchical Aggregation in Edge Computing<br /> |speaker=Jianqi<br /> |date=2022-6-27<br /> }}<br /> {{Hist_seminar<br /> |confname= ICDCS 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9546452<br /> |title=Gillis: Serving Large Neural Networks in Serverless Functions with Automatic Model Partitioning<br /> |speaker=Kun Wang<br /> |date=2022-6-27<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://www.jianguoyun.com/p/DWeMmMMQrvr2CBivtsYEIAA<br /> |title=Multi-Agent Distributed Reinforcement Learningfor Making Decentralized Offloading Decisions<br /> |speaker=Wenjie<br /> |date=2022-6-20<br /> }}<br /> {{Hist_seminar<br /> |confname= Sensys 2021<br /> |link=https://dl.acm.org/doi/abs/10.1145/3485730.3485929<br /> |title=FedMask: Joint Computation and Communication-Efficient Personalized Federated Learning via Heterogeneous Masking<br /> |speaker=Xinyu<br /> |date=2022-6-13<br /> }}<br /> {{Hist_seminar<br /> |confname= Sensys 2021<br /> |link=https://cse.msu.edu/~caozc/papers/sensys21-li.pdf<br /> |title=NELoRa: Towards Ultra-low SNR LoRa Communication with Neural-enhanced Demodulation<br /> |speaker=Kaiwen<br /> |date=2022-6-6<br /> }}<br /> {{Hist_seminar<br /> |confname= SenSys 2021<br /> |link=https://www.egr.msu.edu/~mizhang/papers/2021_SenSys_Mercury.pdf<br /> |title=Mercury: Efficient On-Device Distributed DNN Training via Stochastic Importance Sampling<br /> |speaker=Jiajun<br /> |date=2022-5-30<br /> }}<br /> {{Hist_seminar<br /> |confname= ATC 2020<br /> |link=https://www.usenix.org/system/files/atc20-tsai.pdf<br /> |title=Disaggregating Persistent Memory and Controlling Them Remotely: An Exploration of Passive Disaggregated Key-Value Stores<br /> |speaker=Qinyong<br /> |date=2022-5-30<br /> }}<br /> {{Hist_seminar<br /> |confname= TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9184260<br /> |title= Measurement Errors in Range-Based Localization Algorithms for UAVs: Analysis and Experimentation<br /> |speaker=Luwei<br /> |date=2022-5-23<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488426<br /> |title=AMIS:EdgeComputingBasedAdaptiveMobileVideoStreaming<br /> |speaker=Silence<br /> |date=2022-5-23<br /> }}<br /> {{Hist_seminar<br /> |confname= SIGCOMM 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3452296.3472893<br /> |title= XLINK: QoE-driven multi-path QUIC transport in large-scale video services<br /> |speaker=Rong<br /> |date=2022-5-9<br /> }}<br /> {{Hist_seminar<br /> |confname= IoTJ 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9612588<br /> |title=Stepwise Refinement Provenance Scheme for Wireless Sensor Networks<br /> |speaker=Zhuoliu<br /> |date=2022-5-9<br /> }}<br /> {{Hist_seminar<br /> |confname= IPSN 2022<br /> |link=http://www.carloalbertoboano.com/documents/yang22emu.pdf<br /> |title= EMU: Increasing the Performance and Applicability of LoRa through Chirp Emulation, Snipping, and Multiplexing<br /> |speaker=Wenliang<br /> |date=2022-4-29<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2022<br /> |link=https://www.usenix.org/system/files/nsdi22-paper-chen_jun_lin.pdf<br /> |title=Starlight: Fast Container Provisioning on the Edge and over the WAN<br /> |speaker=Jiangshu<br /> |date=2022-4-29<br /> }}<br /> {{Hist_seminar<br /> |confname= AAAI 2022<br /> |link=https://www.aaai.org/AAAI22Papers/AAAI-6846.YueT.pdf<br /> |title= FedProto: Federated Prototype Learning across Heterogeneous Clients<br /> |speaker=Jianqi<br /> |date=2022-4-22<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2022<br /> |link=https://www.usenix.org/system/files/nsdi22-paper-xu_jingao.pdf<br /> |title=SwarmMap: Scaling Up Real-time Collaborative Visual SLAM at the Edge<br /> |speaker=Jianfei<br /> |date=2022-4-12<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2022<br /> |link=https://www.usenix.org/system/files/nsdi22-paper-li_chenning.pdf<br /> |title=CurvingLoRa to Boost LoRa Network Throughput via Concurrent Transmission<br /> |speaker=Xiong<br /> |date=2022-4-15<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://cse.msu.edu/~caozc/papers/infocom22-li.pdf<br /> |title=CurveALOHA: Non-linear Chirps Enabled High Throughput Random Channel Access for LoRa<br /> |speaker=Xiong<br /> |date=2022-4-15<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://arxiv.org/pdf/2112.11818v1.pdf<br /> |title=Decentralized Task Offloading in Edge Computing: A Multi-User Multi-Armed Bandit Approach<br /> |speaker=Wenjie<br /> |date=2022-4-8<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://www2.cs.sfu.ca/~jcliu/Papers/casva22.pdf<br /> |title=CASVA: Configuration-Adaptive Streaming for Live Video Analytics<br /> |speaker=Shiqi<br /> |date=2022-4-8<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2022<br /> |link=https://xiaolongbupt.github.io/homepage_files/%5BPaper%5DWiRa_INFOCOM2022.pdf<br /> |title=WiRa: Enabling Cross-Technology Communication from WiFi to LoRa with IEEE 802.11ax<br /> |speaker=Kaiwen<br /> |date=2022-3-12<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488843<br /> |title=EdgeDuet: Tiling Small Object Detection for Edge Assisted Autonomous Mobile Vision<br /> |speaker=Xianyang<br /> |date=2022-3-12<br /> }}<br /> {{Hist_seminar<br /> |confname= INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488741<br /> |title=Edge-assisted Online On-device Object Detection for Real-time Video Analytics<br /> |speaker=Silence<br /> |date=2022-3-4<br /> }}<br /> ====2021====<br /> {{Hist_seminar<br /> |confname= MobiCom 2021<br /> |link=https://dl.acm.org/doi/abs/10.1145/3447993.3483274<br /> |title=Flexible high-resolution object detection on edge devices with tunable latency<br /> |speaker=Rong<br /> |date=2021-12-24<br /> }}<br /> {{Hist_seminar<br /> |confname= TPDS 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9497712<br /> |title=Energy-Efficient Offloading for DNN-Based Smart IoT Systems in Cloud-Edge Environments<br /> |speaker=Wenjie<br /> |date=2021-12-24<br /> }}<br /> {{Hist_seminar<br /> |confname= TMC 2022<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9119834<br /> |title=Objective-Variable Tour Planning for Mobile Data Collection in Partitioned Sensor Networks<br /> |speaker=Zhuoliu<br /> |date=2021-12-24<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom 2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3372224.3419193<br /> |title=Nephalai: towards LPWAN C-RAN with physical layer compression<br /> |speaker=Wenliang<br /> |date=2021-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom 2021<br /> |link= https://dl.acm.org/doi/10.1145/3447993.3483242<br /> |title=EMP: edge-assisted multi-vehicle perception<br /> |speaker=Jiangshu<br /> |date=2021-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname= NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21spring-xu.pdf<br /> |title=Move Fast and Meet Deadlines: Fine-grained Real-time Stream Processing with Cameo<br /> |speaker=Jianfei<br /> |date=2021-12-10<br /> }}<br /> {{Hist_seminar<br /> |confname= ICML 2021<br /> |link= https://arxiv.org/pdf/2105.10056.pdf<br /> |title=Data-Free Knowledge Distillation for Heterogeneous Federated Learning<br /> |speaker=Jianqi<br /> |date=2021-12-10<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname= TWC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=939476<br /> |title=OMUS: Efficient Opportunistic Routing in Multi-Modal Underwater Sensor Networks<br /> |speaker=Xianyang<br /> |date=2021-12-3<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom 2021<br /> |link= https://dl.acm.org/doi/pdf/10.1145/3447993.3483250<br /> |title=Combating link dynamics for reliable lora connection in urban settings<br /> |speaker=Wangxiong<br /> |date=2021-12-3<br /> }}<br /> {{Hist_seminar<br /> |confname= IMWUT 2021<br /> |link= https://dl.acm.org/doi/pdf/10.1145/3478117<br /> |title=A City-Wide Crowdsourcing Delivery System with Reinforcement Learning<br /> |speaker=Wenjie<br /> |date=2021-12-3<br /> }}<br /> {{Hist_seminar<br /> |confname= TWC 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9505263<br /> |title=Mega Satellite Constellation System Optimization: From Network Control Structure Perspective<br /> |speaker=Shiqi<br /> |date=2021-11-19<br /> }}<br /> {{Hist_seminar<br /> |confname= TWC 2021<br /> |link= https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9357996<br /> |title=Distance-Aware Relay Selection in an Energy-Efficient Discovery Protocol for 5G D2D Communication<br /> |speaker=Luwei<br /> |date=2021-11-19<br /> }}<br /> {{Hist_seminar<br /> |confname= ToN <br /> |link=https://ieeexplore.ieee.org/document/9525630<br /> |title=Adaptive Configuration Selection and Bandwidth Allocation for Edge-Based Video Analytics<br /> |speaker=Rong<br /> |date=2021-11-12<br /> }}<br /> {{Hist_seminar<br /> |confname= MobiCom'21<br /> |link= https://dl.acm.org/doi/abs/10.1145/3447993.3483268<br /> |title=PCube: scaling LoRa concurrent transmissions with reception diversities<br /> |speaker=Kaiwen<br /> |date=2021-11-12<br /> }}<br /> {{Hist_seminar<br /> |confname= IMWUT 2021<br /> |link= https://dl.acm.org/doi/pdf/10.1145/3478117<br /> |title=A City-Wide Crowdsourcing Delivery System with Reinforcement Learning<br /> |speaker=Wenjie<br /> |date=2021-11-12<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS 2021<br /> |link=https://ieeexplore.ieee.org/document/9546470/<br /> |title=Defuse: A Dependency-Guided Function Scheduler to Mitigate Cold Starts on FaaS Platforms<br /> |speaker=Linyuanqi Zhang<br /> |date=2021-11-05<br /> }}<br /> {{Hist_seminar<br /> |confname=ICLR 2021<br /> |link=https://paperswithcode.com/paper/fedmix-approximation-of-mixup-under-mean-1<br /> |title=FedMix: Approximation of Mixup under Mean Augmented Federated Learning<br /> |speaker=Jianqi Liu<br /> |date=2021-11-05<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9488721<br /> |title=Enhanced Flooding-Based Routing Protocol for Swarm UAV Networks: Random Network Coding Meets Clustering<br /> |speaker=Luwei<br /> |date=2021-10-29<br /> }}<br /> {{Hist_seminar<br /> |confname=IEEE Communications Surveys &amp; Tutorials 2018<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8386758<br /> |title=Routing in Multi-Hop Cellular Device-to-Device(D2D) Networks: A Survey<br /> |speaker=Wenjie<br /> |date=2021-10-29<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21-landa.pdf<br /> |title=Staying Alive: Connection Path Reselection at the Edge<br /> |speaker=Zhuoliu<br /> |date=2021-10-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2021<br /> |link=https://ieeexplore.ieee.org/document/9488714<br /> |title=PolarTracker: Attitude-aware Channel Access for Floating Low Power Wide Area Networks<br /> |speaker=Wenliang<br /> |date=2021-10-15<br /> }}<br /> {{Hist_seminar<br /> |confname=SIGCOMM 2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3452296.3472897<br /> |title=Hoplite: efficient and fault-tolerant collective communication for task-based distributed systems<br /> |speaker=Xianyang<br /> |date=2021-10-08<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21-tollman.pdf<br /> |title=EPaxos Revisited<br /> |speaker=Jianfei<br /> |date=2021-10-08<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom 2021<br /> |link=https://dl.acm.org/doi/10.1145/3447993.3448630<br /> |title=A community-driven approach to democratize access to satellite ground stations<br /> |speaker=Rong Cong<br /> |date=2021-09-24<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI 2021<br /> |link=https://www.usenix.org/system/files/nsdi21-huang.pdf<br /> |title=Toward Nearly-Zero-Error Sketching via Compressive Sensing<br /> |speaker=Xiong Wang<br /> |date=2021-09-24<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9055089<br /> |title=Real-Time Detection for Drowsy Driving via Acoustic Sensing on Smartphones<br /> |speaker=Shiqi Hu<br /> |date=2021-09-17<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiHoc2021<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3466772.3467054<br /> |title=DeepLoRa: Fingerprinting LoRa Devices at Scale Through Deep Learning and Data Augmentation<br /> |speaker=Wenliang Mao<br /> |date=2021-09-17<br /> }}<br /> {{Hist_seminar<br /> |confname=IoTJ2021<br /> |link=https://ieeexplore.ieee.org/abstract/document/9386238<br /> |title=D2D-Enabled Mobile-Edge Computation Offloading for Multiuser IoT Network<br /> |speaker=Wenjie Huang<br /> |date=2021-09-17<br /> }}<br /> {{Hist_seminar<br /> |confname=talk<br /> |link=https://mobinets.cn/site/Resource:Paper_Carnival_2021<br /> |title= Sharing the state-of-the-art research works <br /> |speaker=All<br /> |date=2021-09-03<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'2020<br /> |link=https://ieeexplore.ieee.org/abstract/document/9259397<br /> |title= SCLoRa: Leveraging Multi-Dimensionality in Decoding Collided LoRa Transmissions<br /> |speaker=Wenliang Mao<br /> |date=2021-06-21<br /> }}<br /> {{Hist_seminar<br /> |confname=HotNets'2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3422604.3425938<br /> |title= &quot;Internet from Space&quot; without Inter-satellite Links?<br /> |speaker=Jiangshu Liu<br /> |date=2021-06-21<br /> }}<br /> {{Hist_seminar<br /> |confname=HotNets'2020<br /> |link=https://dl.acm.org/doi/pdf/10.1145/3422604.3425926<br /> |title= A Distributed and Hybrid Ground Station Network for Low Earth Orbit Satellites<br /> |speaker=Jiangshu Liu<br /> |date=2021-06-21<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title= Path Reconstruction in Wireless Network<br /> |speaker=Luwei Fu<br /> |date=2021-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'2021<br /> |link=https://www.jianguoyun.com/p/DfMXogcQ_LXjBxiz6PkD<br /> |title= Mobility- and Load-Adaptive Controller Placement and Assignment in LEO Satellite Networks<br /> |speaker=Linyuanqi Zhang<br /> |date=2021-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title= Data Storage Management at Edge <br /> |speaker=Rong CONG<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=CONEXT Workshop 2019<br /> |link=https://dl.acm.org/doi/10.1145/3359993.3366644<br /> |title=Edge Data Repositories - The design of a store-process-send system at the Edge<br /> |speaker=Rong CONG<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=HotEdge 2018<br /> |link=https://www.usenix.org/conference/hotedge18/presentation/psaras<br /> |title=Mobile Data Repositories at the Edge<br /> |speaker=Rong CONG<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM 2021<br /> |link=https://www.researchgate.net/publication/346643946_Store_Edge_Networked_Data_SEND_A_Data_and_Performance_Driven_Edge_Storage_Framework<br /> |title=Store Edge Networked Data(SEND): A Data and Performance Driven Edge Storage Framework<br /> |speaker=Jiangshu Liu<br /> |date=2021-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'2020<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9200665<br /> |title=Partial Computation Offloading and Adaptive Task Scheduling for 5G-enabled Vehicular Networks<br /> |speaker=Wenjie Huang<br /> |date=2021-05-25<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Two problems about my work: data collection and mobile charging scheme<br /> |speaker=Jianfei Zhang<br /> |date=2021-05-25<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'2021<br /> |link=http://wrap.warwick.ac.uk/145720/1/WRAP-trust-trackers-computation-offloading-edge-based-IoT-networks-Bradbury-2020.pdf<br /> |title=Trust Trackers for Computation Offloading in Edge-Based IoT Networks<br /> |speaker=Chang Shu<br /> |date=2021-05-12<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'2021<br /> |link=https://cse.msu.edu/~caozc/papers/infocom21-liu.pdf<br /> |title=Jamming of LoRa PHY and Countermeasure<br /> |speaker=Xiong Wang<br /> |date=2021-05-12<br /> }}<br /> {{Hist_seminar<br /> |confname=SenSys'20<br /> |link=https://dl.acm.org/doi/10.1145/3384419.3430770<br /> |title=SLoRa:Towards Secure LoRa Communications with Fine-grained Physical Layer Features<br /> |speaker=Wenliang Mao<br /> |date=2021-04-20<br /> }}<br /> {{Hist_seminar<br /> |confname=SenSys'20<br /> |link=https://dl.acm.org/doi/10.1145/3384419.3430731<br /> |title=Combating interference for long range LoRa sensing<br /> |speaker=Weifeng Gao<br /> |date=2021-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=TechReport<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=MA Ced federated learning<br /> |speaker=Xiaosong Wang<br /> |date=2021-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=TVT'2020<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=9238415<br /> |title= Energy-Efficient and Delay-Fair Mobile Computation Offloading <br /> |speaker=Wenjie Huang<br /> |date=2021-4-7<br /> }}<br /> {{Hist_seminar<br /> |confname=TVT'2020<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8840972<br /> |title= A Utility Model for Photo Selection in Mobile Crowdsensing<br /> |speaker=Changsheng Liu<br /> |date=2021-4-7<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8960404<br /> |title= An Application Placement Technique for Concurrent IoT Applications in Edge and Fog Computing Environments<br /> |speaker=Jiwei Mo<br /> |date=2021-3-30<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'2021<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8945405<br /> |title= Multi-Task Allocation Under Time Constraints in Mobile Crowdsensing<br /> |speaker=Luwei Fu<br /> |date=2021-3-30<br /> }}<br /> <br /> ====2020====<br /> {{Hist_seminar<br /> |confname=TMC'20<br /> |link=https://ieeexplore.ieee.org/abstract/document/9078842/<br /> |title=A Fuzzy Logic-based On-demand Charging Algorithm for Wireless Rechargeable Sensor Networks with Multiple Chargers<br /> |speaker=Rong Cong<br /> |date=2020-11-19<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=https://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Two problems about my work: data collection and mobile charging scheme<br /> |speaker=Wenjie Huang<br /> |date=2020-11-19<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=<br /> |title=The path planning algorithm for multiple mobile edge servers in EdgeGO<br /> |speaker=Rong Cong<br /> |date=2020-11-18<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=Mobisys20<br /> |link=https://dl.acm.org/doi/10.1145/3386901.3388913<br /> |title=Combating packet collisions using non-stationary signal scaling in LPWANs<br /> |speaker=Wenliang Mao<br /> |date=2020-11-18<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=<br /> |title=Dependency-Aware and Latency-Optimal Service Cache in Edge networks<br /> |speaker=Jiwei Mo<br /> |date=2020-11-18<br /> }}<br /> {{Hist_seminar<br /> |confname=talk<br /> |link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2019<br /> |title=[[Resource:Paper_Carnival_2020|Paper Carnival 2020]]<br /> |speaker=ALL<br /> |date=2020-09-24,25,26<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://infocom2020.ieee-infocom.org/accepted-paper-list-main-conference<br /> |title=Optimizing Federated Learning on Non-IID Data with Reinforcement Learning<br /> |speaker=YuHong Jiang<br /> |date = 2020-5-16<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://arxiv.org/pdf/2002.11850<br /> |title=Joint Optimization of Signal Design and Resource Allocation in Wireless D2D Edge Computing<br /> |speaker=Shiqi Hu<br /> |date=2020-4-20<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://www4.comp.polyu.edu.hk/~csyqzheng/papers/LiteNap-INFOCOM20.pdf<br /> |title=LiteNap: Downclocking LoRa Reception<br /> |speaker=Wenliang Mao<br /> |date=2020-4-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'20<br /> |link=https://arxiv.org/abs/2002.02596<br /> |title=Delay-Optimal Distributed Edge Computing in Wireless Edge Networks<br /> |speaker=Chang Shu<br /> |date= 2020-3-30<br /> }}<br /> {{Hist_seminar<br /> |confname=IoTJ 2018<br /> |link=https://ieeexplore.ieee.org/document/8371243<br /> |title=Over-the-Air Computation for IoT Networks: Computing Multiple Functions With Antenna Arrays<br /> |speaker=Yuhong Jiang<br /> |date=2020-3-23<br /> }}<br /> {{Hist_seminar<br /> |confname=SIGCOMM'19<br /> |link=https://dl.acm.org/doi/abs/10.1145/3341302.3342081<br /> |title=RF-based Inertial Measurement<br /> |speaker=Weifeng Gao<br /> |date=2020-3-16<br /> }}<br /> ====2019====<br /> <br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/3i4wf2M7nD3nbkXbcbx1Do/5ZUGADKwrq6X0AzD4emr9c.pdf<br /> |title=FRAME: Fault Tolerant and Real-Time Messaging for Edge Computing<br /> |speaker=Xiaosong Wang<br /> |date=2019-12-25<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8737456<br /> |title=Intelligent Edge-Assisted Crowdcast with Deep Reinforcement Learning for Personalized QoE<br /> |speaker=Hengwei Deng<br /> |date=2019-12-25<br /> }}<br /> {{Hist_seminar<br /> |confname=ieee communications magazine'18<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8466366<br /> |title=Orchestration of Microservices for IoT Using Docker and Edge Computing<br /> |speaker=Changsheng Liu<br /> |date=2019-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname=Computer Science'13<br /> |link=https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf<br /> |title=Playing Atari with Deep Reinforcement Learning<br /> |speaker=Jie Zhang<br /> |date=2019-12-17<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'19<br /> |link=https://icnp19.cs.ucr.edu/proceedings/MainConference/FullPapers/icnp2019-final8.pdf<br /> |title=Exploiting Rateless Codes and Cross-Layer Optimization for Low-Power Wide-Area Networks<br /> |speaker=Silin Feng<br /> |date=2019-11-13<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/yzgM12TqeMYjWMqMhtP8N/7zRQAZeZ0fbS1oMqRXu5YR.pdf<br /> |title=DMRA: A Decentralized Resource Allocation Scheme for Multi-SP Mobile Edge Computing<br /> |speaker=Jiwei Mo<br /> |date=2019-11-13<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'19<br /> |link=http://www.winlab.rutgers.edu/~luyang/papers/mobicom19_augmented_reality.pdf<br /> |title=Edge Assisted Real-time Object Detection for MobileAugmented Reality<br /> |speaker=Yunpeng Han<br /> |date=2019-11-06<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI'20<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar#<br /> |title=Frequency Configuration for Low-Power Wide-Area Networks in a Heartbeat<br /> |speaker=Xiong Wang<br /> |date=2019-11-06<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiSys'16<br /> |link=https://www.microsoft.com/en-us/research/publication/mobility-modeling-prediction-bike-sharing-systems-2/<br /> |title=Mobility Modeling and Prediction in Bike-Sharing Systems<br /> |speaker=Anqi Yang<br /> |date=2019-10-30<br /> }}<br /> {{Hist_seminar<br /> |confname=Tech. Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar#<br /> |title=LoRa Localization<br /> |speaker=Xuan Yang<br /> |date=2019-10-30<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'19<br /> |link=https://people.cs.uchicago.edu/~junchenj/docs/E2E_Sigcomm19.pdf<br /> |title=E2E: Embracing User Heterogeneity to ImproveQuality of Experience on the Web<br /> |speaker=Jingwei Li<br /> |date=2019-10-23<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://www.cse.ust.hk/~weiwa/papers/cmfl-icdcs19.pdf<br /> |title=CMFL: Mitigating Communication Overhead for Federated Learning<br /> |speaker=Yuhong Jiang<br /> |date=2019-10-23<br /> }}<br /> {{Hist_seminar<br /> |confname=Tech.Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar#<br /> |title=Report on LoRa reliable protocols<br /> |speaker=Wenliang Mao<br /> |date=2019-10-16<br /> }}<br /> {{Hist_seminar<br /> |confname=ICDCS'19<br /> |link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/4s7uYmRKCj0LsGXo56pEeY/6q2XcJvusaWopfasaMSRAA.pdf<br /> |title=Computation Offloading for Mobile-Edge Computing with Multi-user<br /> |speaker=Chang Shu<br /> |date=2019-10-16<br /> }}<br /> <br /> {{Hist_seminar<br /> |confname=Paper_Carnival_2019<br /> |link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2019<br /> |title= [[Resource:Paper_Carnival_2019|Paper Carnival 2019]]<br /> |speaker=ALL<br /> |date=2019-09-28,29,30<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://netarchlab.tsinghua.edu.cn/~junbi/INFOCOM2019-1.pdf<br /> |title=Octans: Optimal Placement of Service Function Chains in Many-Core Systems<br /> |speaker=Yuntong Zhang<br /> |date=2019-05-22<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=https://ieeexplore.ieee.org/abstract/document/8737660<br /> |title=Adaptive Interference-Aware VNF Placement for Service-Customized 5G Network Slices<br /> |speaker=Zhe Wang<br /> |date=2019-05-22<br /> }}<br /> {{Hist_seminar<br /> |confname=Tech. Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Recent progress and further trends on EdgeCloudSim<br /> |speaker=Yunpeng Han<br /> |date=2019-04-19<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'19<br /> |link=https://arxiv.org/pdf/1812.03103.pdf<br /> |title=mD-Track: Leveraging Multi-Dimensionality for Passive Indoor Wi-Fi Tracking<br /> |speaker=Xuan Yang<br /> |date=2019-04-19<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Correctness and Performance for Stateful Chained Network Functions<br /> |speaker=Yunpeng Han<br /> |date=2019-04-19<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Charging Oriented Sensor Placement and Flexible Scheduling in Rechargeable WSN<br /> |speaker=Wenjie Huang<br /> |date=2019-04-12<br /> }}<br /> {{Hist_seminar<br /> |confname=SIGCOMM'13<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Developing a Predictive Model of Quality of Experience for Internet Video<br /> |speaker=Yuhong Jiang<br /> |date=2019-04-12<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Brush like a Dentist: Accurate Monitoring of Toothbrushing via Wrist-Worn Gesture Sensing<br /> |speaker=Jingwei Li<br /> |date=2019-03-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Nomad: An Efficient Consensus Approach for Latency-Sensitive Edge-Cloud Applications<br /> |speaker=Anqi Yang<br /> |date=2019-03-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Winning at the Starting Line: Joint Network Selection and Service Placement for Mobile Edge Computing<br /> |speaker=Chang Shu<br /> |date=2019-03-22<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'19<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Interference Recycling: Exploiting Interfering Signals to Enhance Data Transmission<br /> |speaker=Wenliang Mao<br /> |date=2019-03-22<br /> }}<br /> {{Hist_seminar<br /> |confname=COMST'18<br /> |link=https://ieeexplore.ieee.org/document/8430735/<br /> |title=Small Cells in the Forthcoming 5G/IoT: Traffic Modeling and Deployment Overview<br /> |speaker=Anqi Yang<br /> |date=2019-01-04<br /> }}<br /> <br /> ====2018====<br /> {{Hist_seminar<br /> |confname=SIGCOMM'18<br /> |link=https://conferences.sigcomm.org/events/apnet2018/papers/elastic_sketch.pdf<br /> |title=Elastic Sketch: Adaptive and Fast Network-wide Measurements<br /> |speaker=Wenliang Mao<br /> |date=2018-12-21<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/document/7458131/<br /> |title=Performance analysis of mobile data offloading in heterogeneous networks<br /> |speaker=Yunpeng Han<br /> |date=2018-12-06<br /> }}<br /> {{Hist_seminar<br /> |confname=COMST'18<br /> |link=https://ieeexplore.ieee.org/document/8430735/<br /> |title=Small Cells in the Forthcoming 5G/IoT: Traffic Modelling and Deployment Overview<br /> |speaker=Anqi Yang<br /> |date=2018-12-06<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=http://ieeexplore.ieee.org/document/7272098/<br /> |title=A Reliability-Augmented Particle Filter for Magnetic Fingerprinting based Indoor Localization on Sma<br /> |speaker=Wenjie Huang<br /> |date=2018-11-30<br /> }}<br /> {{Hist_seminar<br /> |confname=ToN'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8519737<br /> |title=A Distributed Computation Offloading Strategy in Small-Cell Networks Integrated With Mobile Edge Computing<br /> |speaker=Yuhong Jiang<br /> |date=2018-11-23<br /> }}<br /> {{Hist_seminar<br /> |confname=ICNP'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8526830<br /> |title=Networking Support For Physical-Layer Cross-Technology Communication<br /> |speaker=Jingwei Li<br /> |date=2018-11-23<br /> }}<br /> {{Hist_seminar<br /> |confname=IoT Journal'18<br /> |link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&amp;arnumber=8361406<br /> |title=Mobile-Edge Computation Offloading for Ultra-Dense IoT Networks<br /> |speaker=Chang Shu<br /> |date=2018-11-16<br /> }}<br /> {{Hist_seminar<br /> |confname=IPSN'17<br /> |link=http://mpc.ece.utexas.edu/media/uploads/publishing/blend_ipsn17.pdf<br /> |title=BLEnd: Practical Continuous Neighbor Discovery for Bluetooth Low Energy<br /> |speaker=Minghang Yang<br /> |date=2018-11-16<br /> }}<br /> {{Hist_seminar<br /> |confname=Topic<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=LoRa Applications (two papers)<br /> |speaker=Xinyuan Huang<br /> |date=2018-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/abstract/document/8476204<br /> |title=Static and Mobile Target k-Coverage in Wireless Rechargeable Sensor Networks<br /> |speaker=Shuowei Chen<br /> |date=2018-10-19<br /> }}<br /> {{Hist_seminar<br /> |confname=EWSN'17<br /> |link=https://dl.acm.org/citation.cfm?id=3108015<br /> |title=MOR: Multichannel Opportunistic Routing for Wireless Sensor Networks<br /> |speaker=Xuan Yang<br /> |date=2018-10-12<br /> }}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/abstract/document/7874147<br /> |title= Hermes: Latency Optimal Task Assignment for Resource-constrained Mobile Computing<br /> |speaker=Yunpeng Han<br /> |date=2018-10-12<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://www.youtube.com/watch?v=e02p7813kN8<br /> |title=FoggyCache: Cross-Device Approximate Computation Reuse<br /> |speaker=Jingwei Li<br /> |date=2018-09-30<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8406950/<br /> |title=Knowledge-centric proactive edge caching over mobile content distribution network<br /> |speaker=Anqi Yang<br /> |date=2018-09-21<br /> }}<br /> {{Hist_seminar<br /> |confname=TWC'18<br /> |link=https://ieeexplore.ieee.org/abstract/document/8443421/<br /> |title=Enhancing Video Rate Adaptation with Mobile Edge Computing and Caching in Software-defined Mobile Ne<br /> |speaker=Yuhong Jiang<br /> |date=2018-09-21<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://netlab.dcs.gla.ac.uk/uploads/files/4239e2a52ef02c46fbdccb8ad0de1448.pdf<br /> |title=Dynamic,Latency-Optimal vNF Placement at the Network Edge<br /> |speaker=Latency-Optimal vNF Placement at the Network Edge<br /> |date=Chang Shu}}<br /> {{Hist_seminar<br /> |confname=TMC'17<br /> |link=https://ieeexplore.ieee.org/abstract/document/7572937/<br /> |title=Neighbor Discovery and Rendezvous Maintenance with Extended Quorum Systems for Mobile Applications<br /> |speaker=Minghang Yang<br /> |date=2018-09-14<br /> }}<br /> {{Hist_seminar<br /> |confname=Special Session<br /> |link=http://mobinets.org/seminar/carnival18mns/program.pdf<br /> |title=3-day discussion on recent papers in wireless,networking and mobile<br /> |speaker=networking and mobile&lt;/a&gt;<br /> |date=Chang Shu}}<br /> {{Hist_seminar<br /> |confname=IPSN'18<br /> |link=https://dl.acm.org/citation.cfm?id=3207955<br /> |title=Charm: Exploiting Geographical Diversity Through Coherent Combining in Low-Power Wide-Area Networks<br /> |speaker=Weifeng Gao<br /> |date=2018-06-15<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=http://grid.hust.edu.cn/fmliu/vnf-scaling-infocom1<br /> |title=Adaptive VNF Scaling and Flow Routing with Proactive Demand Prediction<br /> |speaker=Chang Shu<br /> |date=2018-06-15<br /> }}<br /> {{Hist_seminar<br /> |confname=ComMag'17<br /> |link=https://ieeexplore.ieee.org/document/8004165/<br /> |title=The Algorithmic Aspects of Network Slicing<br /> |speaker=Yunpeng Han<br /> |date=2018-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=IPSN'18<br /> |link=https://dl.acm.org/citation.cfm?id=3207954<br /> |title=Continuous Wireless Link Rates for Internet of Things<br /> |speaker=Luqi Yang<br /> |date=2018-06-08<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://www.researchgate.net/publication/325190993<br /> |title=TwinBee: Reliable Physical-Layer Cross-Technology Communication with Symbol-Level Coding<br /> |speaker=Xinyuan Huang<br /> |date=2018-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=Invited Tech.Rep.<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Report on recent research progress<br /> |speaker=Songfan Li<br /> |date=2018-06-01<br /> }}<br /> {{Hist_seminar<br /> |confname=Special Session<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=Scheduling Algorithms for Resource-Constrained Systems<br /> |speaker=Prof. Dakai Zhu from UTSA<br /> |date=2018-05-28<br /> }}<br /> {{Hist_seminar<br /> |confname=CVPR'17<br /> |link=https://ieeexplore.ieee.org/document/8099631/<br /> |title=Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning<br /> |speaker=Hui Cao<br /> |date=2018-05-21<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=http://people.umass.edu/hcai/<br /> |title=Self-Adapting Quorum-Based Neighbor Discovery in Wireless Sensor Networks<br /> |speaker=Minghang Yang<br /> |date=2018-05-21<br /> }}<br /> {{Hist_seminar<br /> |confname=Special Session<br /> |link=http://mobinets.org/index.php?title=Resource:Seminar<br /> |title=From Location to Activity: Human-centric Sensing and Analytics<br /> |speaker=Prof. Tao Gu<br /> |date=2018-05-11<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=#<br /> |title=LipPass: Lip Reading-based User Authentication on Smartphones Leveraging Acoustic Signals<br /> |speaker=Shuowei Chen<br /> |date=2018-04-27<br /> }}<br /> {{Hist_seminar<br /> |confname=JSAC'17<br /> |link=https://ieeexplore.ieee.org/document/8058433<br /> |title=QoE-Aware and Reliable Traffic Steering for Service Function Chaining in Mobile Networks<br /> |speaker=Zhe Wang<br /> |date=2018-04-27<br /> }}<br /> {{Hist_seminar<br /> |confname=JSAC'17<br /> |link=http://rboutaba.cs.uwaterloo.ca/Papers/Journals/20<br /> |title=Distributed Service Function Chaining<br /> |speaker=Yuntong Zhang<br /> |date=2018-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://arxiv.org/pdf/1801.05868<br /> |title=Joint Service Caching and Task Offloading for Mobile Edge Computing in Dense Networks<br /> |speaker=Zi Wang<br /> |date=2018-04-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'18<br /> |link=https://arxiv.org/pdf/1712.06056.pdf<br /> |title=One-Hop Out-of-Band Control Planes for Low-Power Multi-Hop Wireless Networks<br /> |speaker=Chang Shu<br /> |date=2018-03-16<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'16<br /> |link=https://pdfs.semanticscholar.org/8e22/6c40a8c056dc<br /> |title=OpenBox: A Software-De?ned Framework for Developing,Deploying,and Managing Network Functions<br /> |speaker=Deploying<br /> |date=and Managing Network Functions&lt;/a&gt;}}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=https://pdfs.semanticscholar.org/fa3b/9634b6057b3f<br /> |title=Empowering Low-Power Wide Area Networks in Urban Settings<br /> |speaker=Weifeng Gao<br /> |date=2018-02-02<br /> }}<br /> {{Hist_seminar<br /> |confname=ComMag16<br /> |link=http://ieeexplore.ieee.org/abstract/document/81988<br /> |title=Hypergraph Theory: Applications in 5G Heterogeneous Ultra-Dense Networks<br /> |speaker=Yunpeng Han<br /> |date=2018-01-26<br /> }}<br /> {{Hist_seminar<br /> |confname=TCST'17<br /> |link=http://ieeexplore.ieee.org/abstract/document/82372<br /> |title=Optimal UAV Route Planning for Coverage Search of Stationary Target in River<br /> |speaker=Hui Cao<br /> |date=2018-01-26<br /> }}<br /> <br /> ====2017====<br /> <br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://www.ntu.edu.sg/home/junluo/documents/Refle<br /> |title=ReflexCode: Coding with Superposed Reflection Light for LED-Camera Communication<br /> |speaker=Xinyuan Huang<br /> |date=2017-12-08<br /> }}<br /> {{Hist_seminar<br /> |confname=Proc. IEEE 2016<br /> |link=http://ieeexplore.ieee.org/document/7423655/<br /> |title=Using Smart Edge IoT Devices for Safer,Rapid Response With Industry IoT Control Operations<br /> |speaker=Rapid Response With Industry IoT Control Operations&lt;/a&gt;<br /> |date=Minghang Yang}}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://ieeexplore.ieee.org/document/8057039/<br /> |title=Approximation Algorithms for The NFV Service Distribution Problem<br /> |speaker=Yuntong Zhang<br /> |date=2017-11-24<br /> }}<br /> {{Hist_seminar<br /> |confname=CCS'17<br /> |link=https://endchan.xyz/.media/50cf379143925a3926298f8<br /> |title=DolphinAtack: Inaudible Voice Commands<br /> |speaker=Zifei Zhao<br /> |date=2017-11-24<br /> }}<br /> {{Hist_seminar<br /> |confname=NSDI'17<br /> |link=https://www.usenix.org/conference/nsdi17/technical<br /> |title=Improving User Perceived Page Load Times Using Gaze<br /> |speaker=Yaoyao Pang<br /> |date=2017-11-17<br /> }}<br /> {{Hist_seminar<br /> |confname=CoNEXT'16<br /> |link=https://dl.acm.org/citation.cfm?id=2999602<br /> |title=Flurries: Countless Fine-Grained NFs for Flexible Per-Flow Customization<br /> |speaker=Zhe Wang<br /> |date=2017-11-17<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://dl.acm.org/citation.cfm?id=3117843<br /> |title=PassiveVLC: Enabling Practical Visible Light Backscatter Communication for Battery-free IoT Applicat<br /> |speaker=Weifeng Gao<br /> |date=2017-11-10<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://ieeexplore.ieee.org/document/8057229/<br /> |title=Service Chain Embedding with Maximum Flow in Software-defined Network and Application to The Next-Ge<br /> |speaker=Chang Shu<br /> |date=2017-11-10<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumbe<br /> |title=BAC: Bandwidth-Aware Compression for EfficientLive Migration of Virtual Machines<br /> |speaker=Yunpeng Han<br /> |date=2017-11-03<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://dl.acm.org/ft_gateway.cfm?id=3117816&amp;ftid=<br /> |title=WEBee: Physical-Layer Cross-Technology Communication via Emulation<br /> |speaker=Shuowei Chen<br /> |date=2017-11-03<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=http://conferences.sigcomm.org/sigcomm/2017/files/<br /> |title=NFVnice: Dynamic Backpressure and Scheduling for NFV Service Chains<br /> |speaker=Hui Cao<br /> |date=2017-10-27<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'17<br /> |link=https://kabru.eecs.umich.edu/wordpress/wp-content/<br /> |title=Continuous Authentication for Voice Assistants<br /> |speaker=Heng Yuan<br /> |date=2017-10-27<br /> }}<br /> {{Hist_seminar<br /> |confname=TWC'17<br /> |link=http://ieeexplore.ieee.org/document/7929399/<br /> |title=Computation Offloading and Resource Allocation in Wireless Cellular Networks With Mobile Edge Computing<br /> |speaker=Xinyuan Huang<br /> |date=2017-10-20<br /> }}<br /> {{Hist_seminar<br /> |confname=ToN'17<br /> |link=http://ieeexplore.ieee.org/document/7784410/<br /> |title=Chase: Taming concurrent broadcast for flooding in asynchronous duty cycle networks<br /> |speaker=Minghang Yang<br /> |date=2017-10-20<br /> }}<br /> {{Hist_seminar<br /> |confname=TOSN'17<br /> |link=http://www.comp.nus.edu.sg/~mobashir/Resources/Pap<br /> |title=Improving Performance of Synchronous Transmission-Based Protocols Using Capture Effect over Multicha<br /> |speaker=Luqi Yang<br /> |date=2017-10-13<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=http://conferences.sigcomm.org/sigcomm/2017/files/<br /> |title=Dynamic Service Chaining with Dysco<br /> |speaker=Chang Shu<br /> |date=2017-10-13<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=http://personal.stevens.edu/~ychen6/papers/ER%20Ea<br /> |title=ER: Early Recognition of Inattentive Driving Leveraging Audio Devices on Smartphones<br /> |speaker=Zifei Zhao<br /> |date=2017-09-29<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=https://thawproject.files.wordpress.com/2017/04/li<br /> |title=LightTouch: Securely Connecting Wearables to Ambient Displays with User Intent<br /> |speaker=Yaoyao Pang<br /> |date=2017-09-22<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=https://users.cs.fiu.edu/~pand/publications/17info<br /> |title=Traffic Aware Placement of Interdependent NFV Middleboxes<br /> |speaker=Zhe Wang<br /> |date=2017-09-22<br /> }}<br /> {{Hist_seminar<br /> |confname=SigComm'17<br /> |link=https://people.cs.clemson.edu/~hongxih/papers/SIGC<br /> |title=NFP: Enabling Network Function Parallelism in NFV<br /> |speaker=Yuntong Zhang<br /> |date=2017-09-22<br /> }}<br /> {{Hist_seminar<br /> |confname=NFV-SDN'16<br /> |link=https://www.net.t-labs.tu-berlin.de/~stefan/o4sdi1<br /> |title=Efficient service Graph Embedding: A Practical Approach<br /> |speaker=Chang Shu<br /> |date=2017-09-11<br /> }}<br /> {{Hist_seminar<br /> |confname=SenSys'17<br /> |link=http://www.simonduquennoy.net<br /> |title=Network-wide Consensus Utilizing the Capture Effect in Low-power Wireless Networks<br /> |speaker=Weifeng Gao<br /> |date=2017-09-11<br /> }}<br /> {{Hist_seminar<br /> |confname=INFOCOM'17<br /> |link=https://arxiv.org/abs/1612.06507<br /> |title=Survivable and Bandwidth Guaranteed Embe<br /> |speaker=Yuntong Zhang<br /> |date=2017-06-26<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'15<br /> |link=<br /> |title=Survivable and Bandwidth Guaranteed Embedding of Virtual Clusters in Cloud Data Centers<br /> |speaker=Yuntong Zhang<br /> |date=2017-06-26<br /> }}<br /> {{Hist_seminar<br /> |confname=MobiCom'15<br /> |link=https://www.sigmobile.org/mobicom/2015/papers/p9<br /> |title=Keystroke Recognition Using WiFi Signals<br /> |speaker=Weiwang Li<br /> |date=2017-06-26<br /> }}<br /> &lt;!--{{Resource:Previous_Seminars}}--&gt;<br /> <br /> ===Instructions===<br /> 请使用Latest_seminar和Hist_seminar模板更新本页信息. <br /> ** 修改时间和地点信息<br /> ** 将当前latest seminar部分的code复制到[[Resource:Previous_Seminars|这个页面]]中<br /> ** 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=<br /> ** 填入latest seminar各字段信息<br /> ** link请务必不要留空，如果没有link则填本页地址 https://mobinets.org/index.php?title=Resource:Seminar<br /> <br /> *格式说明<br /> ** Latest_seminar: <br /> &lt;blockquote&gt;&lt;small&gt;<br /> {{Latest_seminar<br /> &lt;br&gt;|confname=<br /> &lt;br&gt;|link=<br /> &lt;br&gt;|title=<br /> &lt;br&gt;|speaker=<br /> &lt;br&gt;}}<br /> &lt;/small&gt;<br /> &lt;/blockquote&gt;<br /> ** Hist_seminar<br /> &lt;blockquote&gt;&lt;small&gt;<br /> {{Hist_seminar<br /> &lt;br&gt;|confname=<br /> &lt;br&gt;|link=<br /> &lt;br&gt;|title=<br /> &lt;br&gt;|speaker=<br /> &lt;br&gt;|date=<br /> &lt;br&gt;}}<br /> &lt;/small&gt;&lt;/blockquote&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:%E6%8B%94%E5%B0%96%E8%AE%A1%E5%88%92%E7%BA%B3%E6%96%B0&diff=3459 2025-12-09T02:30:49Z

<p>Zhiwei: </p> <hr /> <div>{{Note|请同学们参考下列项目需求，如对题目描述有疑问，可以直接邮件联系学长学姐。总的原则：<br /> * 这里列出的是相对直观、易于上手的题目，周期大概在一学期以内。<br /> * 请同学们做好时间投入的准备（建议每周≥1.5天），否则效果一般不会好。<br /> * 在实验室期间资源都可以共享，有需求可以随时提出。<br /> }}<br /> # '''地点'''：4号科研楼A527（学校西门进来右手边那栋楼）<br /> # '''申请方式'''：请提前发邮件到&lt;code&gt;zhaosheng@mobinets.org&lt;/code&gt;，说明感兴趣的项目（可多选）。或者直接添加[https://www.feishu.cn/invitation/page/add_contact/?token=e35m3bc6-3dc2-41ad-bb44-5122d3ece165&amp;amp;unique_id=I72w_l6DrnD0dN1rHY1CXA== 赵老师飞书]。<br /> <br /> === 1. 多无人承重任务协作 ===<br /> [[File:DroneCarry.png|thumb|多机协作承重]]<br /> * 参与同学：1-2名<br /> * 联系学长：周羿 &lt;code&gt;&lt;u&gt;zhouyi&lt;/u&gt;@mobinets.org&lt;/code&gt;<br /> * 课题描述：多无人机自主决策协作搬运任务<br /> *# 基于大疆无人机<br /> *# 基于边端协同框架<br /> * 技能训练：<br /> *# Jetson边缘计算平台<br /> *# 视频流处理<br /> * 项目周期：2025-2026学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> <br /> === 2. Rings2.0基于LLM的代码生成 ===<br /> [[File:CodeGen.png|thumb|跨域代码生成]]<br /> * 参与同学：1-2名<br /> * 联系学长：刘栢荣 &lt;code&gt;&lt;u&gt;bairong&lt;/u&gt;@mobinets.org&lt;/code&gt;<br /> * 课题描述：跨域、稳定的代码生成<br /> *# 基于LLM+TransLang<br /> *# 多域多模<br /> * 技能训练：<br /> *# 大模型的使用与微调<br /> *# 代码评价<br /> *# 代码拼接<br /> * 项目周期：2025-2026学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> <br /> &lt;!--<br /> === 基于边缘计算的开放场景数字孪生 ===<br /> [[File:Dt527mr.png|thumb|基于边缘计算的数字孪生系统]]<br /> * 参与同学：2名<br /> * 联系学姐：汪洋，刘栢荣 &lt;code&gt;{&lt;u&gt;wangyang&lt;/u&gt;, &lt;u&gt;bairong&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：<br /> *# 基于图像的实时姿态估计和轨迹追踪<br /> *# 基于边缘平台的推理模型<br /> *# 3D模型框架及开发<br /> * 训练技能：<br /> *# ReID相关论文与实现<br /> *# 熟悉并使用Jetson边缘计算平台<br /> *# Unity开发<br /> <br /> * 项目周期：24-25学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 专利2项、学术论文1篇<br /> <br /> === 基于边缘的实时体积视频编码（Telepresence） ===<br /> [[File:Volu.gif|thumb|体积视频点云编码]]<br /> * 参与同学：2名<br /> * 联系学姐：王梦凡，吴基易 &lt;code&gt;{&lt;u&gt;mengfan&lt;/u&gt;, &lt;u&gt;jiyi&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：<br /> *# 利用普通摄像头采集体积视频<br /> *# 设计高效八叉树编码方法及分时拼接技术<br /> <br /> * 技能训练：<br /> *# 熟悉并运用Jetson边缘计算平台<br /> *# 熟悉视频流处理及传输机制<br /> * 项目周期：24-25学年<br /> * 预计产出：<br /> *# 系统1套<br /> *# 学术论文1-2篇<br /> <br /> === 机器人自主跟随算法及系统 ===<br /> [[File:FollowCam.png|thumb|使用的双足机器人跟随]]<br /> * 参与同学：2名<br /> * 联系学长：何佳昊，周羿 &lt;code&gt;{&lt;u&gt;jiahao&lt;/u&gt;, &lt;u&gt;zhouyi&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：在复杂环境中实现机器人的实时自主跟随<br /> *# 基于无人机/双足机器人系统<br /> *# 对环境和跟随目标不做任何限制<br /> * 技能训练：<br /> *# Jetson边缘计算平台<br /> *# 视频流处理<br /> * 项目周期：本学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:%E6%8B%94%E5%B0%96%E8%AE%A1%E5%88%92%E7%BA%B3%E6%96%B0&diff=3458 2025-12-09T02:29:28Z

<p>Zhiwei: </p> <hr /> <div>{{Note|请同学们参考下列项目需求，如对题目描述有疑问，可以直接邮件联系学长学姐。总的原则：<br /> * 这里列出的是相对直观、易于上手的题目，周期大概在一学期以内。<br /> * 请同学们做好时间投入的准备（建议每周≥1.5天），否则效果一般不会好。<br /> * 在实验室期间资源都可以共享，有需求可以随时提出。<br /> }}<br /> # '''地点'''：4号科研楼A527（学校西门进来右手边那栋楼）<br /> # '''申请方式'''：请提前发邮件到&lt;code&gt;zhaosheng@mobinets.org&lt;/code&gt;，说明感兴趣的项目（可多选）。或者直接添加[https://www.feishu.cn/invitation/page/add_contact/?token=e35m3bc6-3dc2-41ad-bb44-5122d3ece165&amp;amp;unique_id=I72w_l6DrnD0dN1rHY1CXA== 赵老师飞书]。<br /> <br /> === 1. 多无人承重任务协作 ===<br /> [[File:DroneCarry.png|thumb|多机协作承重]]<br /> * 参与同学：1-2名<br /> * 联系学长：周羿 &lt;code&gt;&lt;u&gt;zhouyi&lt;/u&gt;@mobinets.org&lt;/code&gt;<br /> * 课题描述：多无人机自主决策协作搬运任务<br /> *# 基于大疆无人机<br /> *# 基于边端协同框架<br /> * 技能训练：<br /> *# Jetson边缘计算平台<br /> *# 视频流处理<br /> * 项目周期：2025-2026学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> <br /> === 2. Rings2.0基于LLM的代码生成 ===<br /> [[File:CodeGen.png|thumb|跨域代码生成]]<br /> * 参与同学：1-2名<br /> * 联系学长：刘栢荣 &lt;code&gt;&lt;u&gt;bairong&lt;/u&gt;@mobinets.org&lt;/code&gt;<br /> * 课题描述：跨域、稳定的代码生成<br /> *# 基于LLM+TransLang<br /> *# 多域多径多案<br /> * 技能训练：<br /> *# 大模型的使用与微调<br /> *# 代码评价<br /> *# 代码拼接<br /> * 项目周期：2025-2026学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> <br /> &lt;!--<br /> === 基于边缘计算的开放场景数字孪生 ===<br /> [[File:Dt527mr.png|thumb|基于边缘计算的数字孪生系统]]<br /> * 参与同学：2名<br /> * 联系学姐：汪洋，刘栢荣 &lt;code&gt;{&lt;u&gt;wangyang&lt;/u&gt;, &lt;u&gt;bairong&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：<br /> *# 基于图像的实时姿态估计和轨迹追踪<br /> *# 基于边缘平台的推理模型<br /> *# 3D模型框架及开发<br /> * 训练技能：<br /> *# ReID相关论文与实现<br /> *# 熟悉并使用Jetson边缘计算平台<br /> *# Unity开发<br /> <br /> * 项目周期：24-25学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 专利2项、学术论文1篇<br /> <br /> === 基于边缘的实时体积视频编码（Telepresence） ===<br /> [[File:Volu.gif|thumb|体积视频点云编码]]<br /> * 参与同学：2名<br /> * 联系学姐：王梦凡，吴基易 &lt;code&gt;{&lt;u&gt;mengfan&lt;/u&gt;, &lt;u&gt;jiyi&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：<br /> *# 利用普通摄像头采集体积视频<br /> *# 设计高效八叉树编码方法及分时拼接技术<br /> <br /> * 技能训练：<br /> *# 熟悉并运用Jetson边缘计算平台<br /> *# 熟悉视频流处理及传输机制<br /> * 项目周期：24-25学年<br /> * 预计产出：<br /> *# 系统1套<br /> *# 学术论文1-2篇<br /> <br /> === 机器人自主跟随算法及系统 ===<br /> [[File:FollowCam.png|thumb|使用的双足机器人跟随]]<br /> * 参与同学：2名<br /> * 联系学长：何佳昊，周羿 &lt;code&gt;{&lt;u&gt;jiahao&lt;/u&gt;, &lt;u&gt;zhouyi&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：在复杂环境中实现机器人的实时自主跟随<br /> *# 基于无人机/双足机器人系统<br /> *# 对环境和跟随目标不做任何限制<br /> * 技能训练：<br /> *# Jetson边缘计算平台<br /> *# 视频流处理<br /> * 项目周期：本学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=File:CodeGen.png&diff=3457 2025-12-09T02:28:47Z

<p>Zhiwei: </p> <hr /> <div></div>

Zhiwei http://mobinets.cn/site/index.php?title=File:DroneCarry.png&diff=3456 2025-12-09T02:26:56Z

<p>Zhiwei: </p> <hr /> <div></div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:%E6%8B%94%E5%B0%96%E8%AE%A1%E5%88%92%E7%BA%B3%E6%96%B0&diff=3455 2025-12-09T02:26:01Z

<p>Zhiwei: </p> <hr /> <div>{{Note|请同学们参考下列项目需求，如对题目描述有疑问，可以直接邮件联系学长学姐。总的原则：<br /> * 这里列出的是相对直观、易于上手的题目，周期大概在一学期以内。<br /> * 请同学们做好时间投入的准备（建议每周≥1.5天），否则效果一般不会好。<br /> * 在实验室期间资源都可以共享，有需求可以随时提出。<br /> }}<br /> # '''地点'''：4号科研楼A527（学校西门进来右手边那栋楼）<br /> # '''申请方式'''：请提前发邮件到&lt;code&gt;zhaosheng@mobinets.org&lt;/code&gt;，说明感兴趣的项目（可多选）。或者直接添加[https://www.feishu.cn/invitation/page/add_contact/?token=e35m3bc6-3dc2-41ad-bb44-5122d3ece165&amp;amp;unique_id=I72w_l6DrnD0dN1rHY1CXA== 赵老师飞书]。<br /> <br /> === 多无人承重任务协作 ===<br /> [[File:DroneFollow.png|thumb|多机协作承重]]<br /> * 参与同学：1-2名<br /> * 联系学长：周羿 &lt;code&gt;&lt;u&gt;zhouyi&lt;/u&gt;@mobinets.org&lt;/code&gt;<br /> * 课题描述：多无人机自主决策协作搬运任务<br /> *# 基于大疆无人机<br /> *# 基于边端协同框架<br /> * 技能训练：<br /> *# Jetson边缘计算平台<br /> *# 视频流处理<br /> * 项目周期：本学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> <br /> === Rings2.0基于LLM的代码生成 ===<br /> [[File:CodeGen.png|thumb|跨域代码生成]]<br /> * 参与同学：1-2名<br /> * 联系学长：刘栢荣 &lt;code&gt;&lt;u&gt;bairong&lt;/u&gt;@mobinets.org&lt;/code&gt;<br /> * 课题描述：跨域、稳定的代码生成<br /> *# 基于LLM+TransLang<br /> *# 多域多径多案<br /> * 技能训练：<br /> *# 大模型的使用与微调<br /> *# 代码评价<br /> *# 代码拼接<br /> * 项目周期：本学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> <br /> &lt;!--<br /> === 基于边缘计算的开放场景数字孪生 ===<br /> [[File:Dt527mr.png|thumb|基于边缘计算的数字孪生系统]]<br /> * 参与同学：2名<br /> * 联系学姐：汪洋，刘栢荣 &lt;code&gt;{&lt;u&gt;wangyang&lt;/u&gt;, &lt;u&gt;bairong&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：<br /> *# 基于图像的实时姿态估计和轨迹追踪<br /> *# 基于边缘平台的推理模型<br /> *# 3D模型框架及开发<br /> * 训练技能：<br /> *# ReID相关论文与实现<br /> *# 熟悉并使用Jetson边缘计算平台<br /> *# Unity开发<br /> <br /> * 项目周期：24-25学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 专利2项、学术论文1篇<br /> <br /> === 基于边缘的实时体积视频编码（Telepresence） ===<br /> [[File:Volu.gif|thumb|体积视频点云编码]]<br /> * 参与同学：2名<br /> * 联系学姐：王梦凡，吴基易 &lt;code&gt;{&lt;u&gt;mengfan&lt;/u&gt;, &lt;u&gt;jiyi&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：<br /> *# 利用普通摄像头采集体积视频<br /> *# 设计高效八叉树编码方法及分时拼接技术<br /> <br /> * 技能训练：<br /> *# 熟悉并运用Jetson边缘计算平台<br /> *# 熟悉视频流处理及传输机制<br /> * 项目周期：24-25学年<br /> * 预计产出：<br /> *# 系统1套<br /> *# 学术论文1-2篇<br /> <br /> === 机器人自主跟随算法及系统 ===<br /> [[File:FollowCam.png|thumb|使用的双足机器人跟随]]<br /> * 参与同学：2名<br /> * 联系学长：何佳昊，周羿 &lt;code&gt;{&lt;u&gt;jiahao&lt;/u&gt;, &lt;u&gt;zhouyi&lt;/u&gt;}@mobinets.org&lt;/code&gt;<br /> * 课题描述：在复杂环境中实现机器人的实时自主跟随<br /> *# 基于无人机/双足机器人系统<br /> *# 对环境和跟随目标不做任何限制<br /> * 技能训练：<br /> *# Jetson边缘计算平台<br /> *# 视频流处理<br /> * 项目周期：本学年<br /> * 预计产出：<br /> *# 算法及系统1套<br /> *# 学术论文1篇<br /> *# 专利2项、参加国家级竞赛<br /> --&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3454 2025-12-05T01:25:39Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-12-05 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = Intermediate reasoning or acting steps have successfully improved large language models (LLMs) for handling various downstream natural language processing (NLP) tasks. When applying LLMs for code generation, recent works mainly focus on directing the models to articulate intermediate natural-language reasoning steps, as in chain-of-thought (CoT) prompting, and then output code with the natural language or other structured intermediate steps. However, such output is not suitable for code translation or generation tasks since the standard CoT has different logical structures and forms of expression with the code. In this work, we introduce the universal code (UniCode) as the intermediate representation. It is a description of algorithm steps using a mix of conventions of programming languages, such as assignment operator, conditional operator, and loop. Hence, we collect an instruction dataset UniCoder-Instruct to train our model UniCoder on multi-task learning objectives. UniCoder-Instruct comprises natural-language questions, code solutions, and the corresponding universal code. The alignment between the intermediate universal code representation and the final code solution significantly improves the quality of the generated code. The experimental results demonstrate that UniCoder with the universal code significantly outperforms the previous prompting methods by a large margin, showcasing the effectiveness of the structural clues in pseudo-code.<br /> |confname =ACL'24<br /> |link = https://arxiv.org/abs/2406.16441<br /> |title= UniCoder: Scaling Code Large Language Model via Universal Code<br /> |speaker=Bairong Liu<br /> |date=2025-12-05<br /> }}<br /> {{Latest_seminar<br /> |abstract =LoRaWANs are envisioned to connect billions of IoT devices through thousands of physically overlapping yet logically orthogonal channels (termed logical channels). These logical channels hold significant potential for enabling highly concurrent scalable IoT connectivity. Large-scale deployments however face strong interference between logical channels. This practical issue has been largely overlooked by existing works but becomes increasingly prominent as LoRaWAN scales up. To address this issue, we introduce Canas, an innovative gateway design that is poised to orthogonalize the logical channels by eliminating mutual interference. To this end, Canas develops a series of novel solutions to accurately extract the meta-information of individual ultra-weak LoRa signals from the received overlapping channels. The meta-information is then leveraged to accurately reconstruct and subtract the LoRa signals over thousands of logical channels iteratively. Real-world evaluations demonstrate that Canas can enhance concurrent transmissions across overlapping logical channels by 2.3× compared to the best known related works.<br /> |confname =TMC'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/11160677<br /> |title= Resolving Inter-Logical Channel Interference for Large-scale LoRa Deployments<br /> |speaker=Mengyu<br /> |date=2025-12-05<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3450 2025-11-28T02:17:18Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-11-28 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = Running deep neural networks (DNNs) on large-scale videos from widely distributed cameras presents two significant challenges. Firstly, video quality for analytical purposes is severely impacted by the camera deployment environment, which is termed Pixel Recession in this paper. Secondly, low-latency video streaming from the source camera to edge servers is greatly hindered by the rapid expansion of video traffic. Despite numerous efforts such as enhancing the video structure, uneven encoding, and filtering frames captured on camera, these methods have proven insufficient to address the challenges at hand. We propose Spliceosome, a novel video analytics system that effectively overcomes the pixel recession and streaming bottlenecks. In brief, Spliceosome 1) recovers from pixel recession by adaptive video knobs (i.e., brightness and contrast) tuning in ARP (anchor region proposal) granularity, and 2) lowers the transmission volume by video thinning, which uses only single-channel information for video encoding. We implemented Spliceosome using only commercial off-the-shelf hardware. Our experimental results demonstrate that Spliceosome outperforms other alternative designs by 4.71-14.47%, 40.94-58.71%, and 14.28% in detection accuracy, end-to-end delay, and efficiency of DNNs inference, respectively.<br /> |confname =ToN'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/10843977<br /> |title= Spliceosome: On-Camera Video Thinning and Tuning for Timely and Accurate Analytics<br /> |speaker=Zhongwei Sun<br /> |date=2025-11-28<br /> }}{{Latest_seminar<br /> |abstract =The rapid expansion of large language models (LLMs) requires the development of extensive GPU clusters, with companies deploying clusters with tens to hundreds of thousands of GPUs. This growth significantly expands the design space for LLM training systems, requiring thorough exploration of different parallelization strategies, communication parameters, congestion control, fabric topology, etc. Current methods require up to 10k simulation experiments to identify optimal configurations, with inadequate exploration leading to significant degradation of training performance. In this paper, we tackle the overlooked problem of efficiently conducting parallel simulation experiments for design space exploration. Our analysis and experiments show that Single-process Multi-experiment (SPME) achieves superior performance by reducing scheduling overhead and optimizing resource utilization, yet remains insufficient for current AI cluster scales. To enhance SPME’s efficacy, we introduce Multiverse, a novel GPU-based AI training simulator. Multiverse leverages the computing throughput of GPUs efficiently with optimizations such as a pull-based synchronization, highfidelity intra-server communication, and a kernel-fusion technique. Extensive experiments validate the accuracy and efficiency of Multiverse, demonstrating less than 3.0% discrepancy with real-world LLM training on clusters of up to 54,000 GPUs, achieving 43.1−73.2X speedup over state-of-the-art CPU-based simulators in various use cases.<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/gui<br /> |title= Accelerating Design Space Exploration for LLM Training Systems with Multi-experiment Parallel Simulation<br /> |speaker=Qinyong<br /> |date=2025-11-28<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3447 2025-11-25T08:21:25Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building ([https://gis.uestc.edu.cn/#/?share=%7B%22type%22%3A%22polygon%22%2C%22MType%22%3A2%2C%22RId%22%3A2%2C%22VId%22%3A1%2C%22id%22%3A7647%2C%22name%22%3A%22%E5%9B%9B%E5%8F%B7%E6%A5%BC%E7%A7%91%E7%A0%94%E6%A5%BCA%E5%8C%BA%22%2C%22lon%22%3A%22103.924924249839%22%2C%22lat%22%3A%2230.756847505265%22%2C%22level%22%3Anull%2C%22from%22%3A%22CMIPS-W%22%2C%22campus%22%3A%22%E6%B8%85%E6%B0%B4%E6%B2%B3%E6%A0%A1%E5%8C%BA%22%7D GIS]), Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Integrated Sensing for Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3444 2025-11-20T15:58:56Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-11-21 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = Entanglement distribution across remote distances is critical for many quantum applications. Currently, the de facto approach for remote entanglement distribution relies on optical fiber for on-the-ground entanglement distribution. However, the fiber-based approach is incapable of global-scale entanglement distribution due to intrinsic limitations. This paper investigates a new hybrid ground-satellite quantum network architecture (QuESat) for global-scale entanglement distribution, integrating an on-the-ground fiber network with a global-scale passive optical network built with low-Earth-orbit satellites. The satellite network provides dynamic construction of photon lightpaths based on near-vacuum beam guides constructed via adjustable arrays of lenses, forwarding photons from one ground station to another with very high efficiency over long distances compared to using fiber. To assess the feasibility and effectiveness of QuESat for global communication, we formulate lightpath provisioning and entanglement distribution problems, considering the orbital dynamics of satellites and the time-varying entanglement demands from ground users. A two-stage algorithm is developed to dynamically configure the beam guides and distribute entanglements, respectively. The algorithm combines randomized and deterministic rounding for lightpath provisioning to enable global connectivity, with optimal entanglement swapping for distributing entanglements to meet users' demands. By developing a ground-satellite quantum network simulator, QuESat achieves multi-fold improvements compared to repeater networks.<br /> |confname = INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/document/11044649<br /> |title= QuESat: Satellite-Assisted Quantum Internet for Global-Scale Entanglement Distribution<br /> |speaker= Yaliang<br /> |date=2025-11-07<br /> }}{{Latest_seminar<br /> |abstract =The global business of transnational enterprises demands geo-distributed databases, where the leader-follower-based consensus protocols are the key to guaranteeing consistency of replicas spread across regions. Compared with traditional databases running in a single data center, determining which node is the leader in consensus protocol has a greater per-formance impact in geo-distributed databases running across multiple data centers. However, the performance of legacy leader management is far from satisfactory due to the network and application dynamics (e.g., network delay, node popularity, operation read-write ratio). This paper proposes GeoLM toward performance-oriented leader management for geo-distributed consensus protocols. GeoLM captures the network and application dynamics and proactively conducts seamless leader handovers with bounded switching costs. Our geo-distributed experimental results show that GeoLM improves performance up to 49.75% over the baselines (e.g., Raft and Geo-Raft) and achieves considerably good performance compared to state-of-the-art consensus protocols (e.g., SwiftPaxos, CURP, and EPaxos).<br /> |confname = INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/document/11044598<br /> |title= GeoLM: Performance-oriented Leader Management for Geo-Distributed Consensus Protocol<br /> |speaker= Linqi Liu<br /> |date=2025-11-07<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3439 2025-10-24T02:41:39Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-10-24 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = Unlike traditional data collection applications (e.g., environment monitoring) that are dominated by uplink transmissions, the newly emerging applications (e.g., device actuation, firmware update, packet reception acknowledgement) also pose ever-increasing demands on downlink transmission capabilities. However, current LoRaWAN falls short in supporting such applications primarily due to downlink-uplink asymmetry. While the uplink can concurrently receive multiple packets, downlink transmission is limited to a single logical channel at a time, which fundamentally hinders the deployment of downlink-hungry applications. To tackle this practical challenge, FDLoRa develops the first-of-its-kind in-band full-duplex LoRa gateway design with novel solutions to mitigate the impact of self-interference (i.e., strong downlink interference to ultra-weak uplink reception), which unleashes the full spectrum for in-band downlink transmissions without compromising the reception of weak uplink packets. Built upon the full-duplex gateways, FDLoRa introduces a new downlink framework to support concurrent downlink transmissions over multiple logical channels of available gateways. Evaluation results demonstrate that FDLoRa boosts downlink capacity by 5.7x compared to LoRaWAN on a three-gateway testbed and achieves 2.58x higher downlink concurrency per gateway than the state-of-the-art.<br /> |confname = Sensys'24<br /> |link = https://dl.acm.org/doi/10.1145/3666025.3699338<br /> |title= FDLoRa: Tackling Downlink-Uplink Asymmetry with Full-duplex LoRa Gateways<br /> |speaker= Kai Chen<br /> |date=2025-10-23<br /> }}{{Latest_seminar<br /> |abstract =Recent years have witnessed a widespread adoption of containers. While containers simplify and accelerate application development, existing container network technologies either incur significant overhead, which hurts performance for distributed applications, or lose flexibility or compatibility, which hinders the widespread deployment in production. We carefully analyze the kernel data path of an overlay network, quantifying the time consumed by each segment of the data path and identifying the extra overhead in an overlay network compared to bare metal. We observe that this extra overhead generates repetitive results among packets, which inspires us to introduce caches within an overlay network. We design and implement ONCache (Overlay Network Cache), a cache-based container overlay network, to eliminate the extra overhead while maintaining flexibility and compatibility. We implement ONCache using the extended Berkeley Packet Filter (eBPF) with only 524 lines of code, and integrate it as a plugin of Antrea. With ONCache, containers attain networking performance akin to that of bare metal. Compared to the standard overlay networks, ONCache improves throughput and request-response transaction rate by 12% and 36% for TCP (20% and 34% for UDP), respectively, while significantly reducing per-packet CPU overhead. Popular distributed applications also benefit from ONCache.<br /> |confname = NSDI'25 <br /> |link = https://www.usenix.org/conference/nsdi25/presentation/lin-shengkai<br /> |title= ONCache: A Cache-Based Low-Overhead Container Overlay Network<br /> |speaker= Daobing Zeng<br /> |date=2025-10-24<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Course:%E5%AD%A6%E6%9C%AF%E8%AE%BA%E6%96%87%E5%86%99%E4%BD%9C%EF%BC%9A%E8%AE%BA%E7%82%B9%E6%91%98%E8%A6%81&diff=3432 2025-10-14T02:33:01Z

<p>Zhiwei: </p> <hr /> <div>==论点摘要测试==<br /> &lt;big&gt;<br /> 阅读研究材料，凝练出其中的关键信息。<br /> * 拟定论文题目<br /> * 论点：针对XX, 提出XX, 解决XX, 达到XX. 揉成一句话。<br /> * 创新点：2-4个，每个创新点1-2句话。<br /> * 摘要：中文200字、英文250字<br /> &lt;/big&gt;<br /> ===研究材料===<br /> &lt;big&gt;股票价格的预测在商业和金融领域具有重要的意义。股票市场的预测在商业界和学术界都受到了广泛的关注。股票市场是一个“有效信息”市场，股票价格充分反映了已经发生的事件，以及那些尚未发生但市场预期会发生的事件对股票价格的影响。这一假设为之后的股票预测工作提供了依据。然而，预测股票价格依然十分困难，因为股票价格受到众多因素的影响。对于单个股票而言，除了国家的货币政策，行业的景气状况等宏观因素，股票上市公司的相关事件等微观因素也会对股票价格产生影响。因此，除了股票自身的价格信息，许多相关工作都将股票相关的新闻信息作为预测股票价格的重要依据。文献[1]中利用实时的新闻信息对股票价格作出预测。他们首先利用线性回归和聚类方法对股票的价格曲线分段，每段时间区间对应价格的上升期和下降期。然后将上升期和下降期内的新闻分别标注为利好消息和利空消息，通过统计方法选择出新闻中的利好和利空特征。最后依据这些新闻中的特征对股票价的涨跌做出预测。该方法忽视了新闻对于股价影响的持续性。TH Nguyen等利用主题模型来预测股票价格。文献[2]提出了一个融合情感和话题的主题模型，并将该模型运用到股票相关新闻的主题分析中。在获得了每个新闻的主题分布向量后，他们将这个主题分布向量加入到股票预测的特征中，最终获得了不错的预测效果。这种主题模型特征是一种通用的文本特征，忽视了金融市场新闻的特殊性。近几年来，深度学习方法在自然语言处理领域取得了许多进展，Xiao Ding等将深度学习方法运用到股票预测领域。文献[3]提出了一种新的事件抽取方法，从新闻中抽取出结构化的事件。这些结构化的事件成为神经网络的输入，用于预测股票价格。随后，在事件抽取工作的基础上，他们在文献[4]中进一步学习出结构化事件的event embedding1，并使用卷积神经网络模型去预测股票价格。这种模型虽然考虑了事件对于股价的持续影响，但是忽略了多个事件对于股价的综合作用。除了与股票相关的新闻信息，大众媒体与社交媒体上的内容也被用于股票预测。不过这些媒体上的内容一般不适用于单个股票的预测，只能对股市整体的情况(道琼斯工业指数、上证指数等)作出预测。文献[5]运用Twitter上的内容对股市的涨跌作出预测。他们使用OpinionFinder2等工具分析Twitter上每天的大众情感，然后将这些情感特征加入到预测模型中，对股市的涨跌作出预测。<br /> 本工作基于股票论坛数据对股价进行预测，首先提出自动化提取大量的论坛数据方法，方法利用了线程并发技术和自适应的线程任务分配策略，达到数据的高效采集，可以应对不同于新闻信息或国家政策信息的股票论坛信息中大量包含的“无效信息”。提出一种论坛数据预处理方法，将论坛数据的情感特征（分为“看涨”或“看跌”）并批量提取。实验结果表明，论坛数据的情感特征提取准确率达到了91%。同时，进一步探究股票情感数据与股价的实际涨跌之间的关系，并提出基于逻辑回归算法的预测方法。值得一提的是，回归算法参数可根据数据内容进行自适应调节，以找到最高的识别精度，相比于现有方法不但提升了预测效率，也保证了预测精度。实验结果表明，提出的股票预测方法相比于传统基于新闻或政策信息的方法在预测精度上提升了15%的准确度，在牛市和熊市环境中准确率甚至达到83%。<br /> &lt;/big&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Template:Gedes_eurosys26&diff=3431 2025-09-30T08:50:39Z

<p>Zhiwei: Zhiwei moved page Template:Gedes eurosys to Template:Gedes eurosys26 without leaving a redirect</p> <hr /> <div>{{Pub<br /> |sn=EuroSys<br /> |authors=Q. Li, Z. Zhao*, G. Min, Z. Wang and L. Fu<br /> |link=https://mobinets.cn/<br /> |title=GeDES: GPU-Driven Discrete Event Network Simulator<br /> |venue=ACM EuroSys<br /> |year=2026<br /> }}<br /> <br /> [[Category:Papers]]</div>

Zhiwei http://mobinets.cn/site/index.php?title=Zhiwei&diff=3430 2025-09-30T08:50:17Z

<p>Zhiwei: </p> <hr /> <div>{{DISPLAYTITLE:&lt;span style=&quot;position: absolute; clip: rect(1px 1px 1px 1px); clip: rect(1px, 1px, 1px, 1px);&quot;&gt;{{FULLPAGENAME}}&lt;/span&gt;}}<br /> [[File:head_2024.jpg|300px|thumb]]<br /> &lt;span style=&quot;font-size:24px&quot;&gt;'''Zhiwei Zhao/赵志为'''<br /> <br /> &lt;big&gt;Professor/PhD Advisor @CSE, UESTC&lt;/big&gt;&lt;/span&gt;<br /> * [[Main_Page|&lt;span style=&quot;font-family:Times; color:green&quot;&gt;M&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:#006ebd&quot;&gt;N&lt;/span&gt;&lt;span style=&quot;font-family:Times; color:red&quot;&gt;&lt;sup&gt;S&lt;/sup&gt;&lt;/span&gt; mobinets group]], [https://www.scse.uestc.edu.cn CSE/UESTC]<br /> * '''Email''': zzw\at\uestc.edu.cn; zhaozw.cs\at\gmail.com<br /> * '''Office''': A535, 4th Research Building, Qingshuihe Campus<br /> * '''[[招生|招生信息]]'''<br /> <br /> I am now a professor at College of Computer Science and Engineering, University of Electronic Science and Technology of China (UESTC). I joined UESTC in 2015 after I got my PhD degree from College of Computer Science, Zhejiang University (ZJU). I received my BS Degree from Xi'an Jiaotong University (XJTU) in 2010. My research interests include low-power and networked systems, edge computing, AIoT, future networks, etc. &lt;u&gt;My research pursuit is to break the border between network and computing, and empower anywhere, anytime and device-free smart life&lt;/u&gt;. I am a member of CCF, ACM and IEEE, and also a big fan of football and Dota.<br /> <br /> ----<br /> ==Selected publications==<br /> To date I have published 100+ peer-reviewed papers on reputable conferences and journals in the areas of edge computing and IoT. Check my full list at [https://scholar.google.com/citations?user=marMFnQAAAAJ&amp;view_op=list_works&amp;sortby=pubdate Google scholar] and our code on [https://github.com/mobinets Github] (edge simulation, offloading, low-power protocols, data traces, etc).<br /> * {{Gedes_eurosys26}}<br /> * {{Tasp_tpds25}}<br /> * {{Loop_tnse25}}<br /> * {{Mmto_tmc25}}<br /> * {{Coopedge_tpds24}}<br /> * {{Slaugfl_tmc24}}<br /> * {{Cpr_infocom23}}<br /> * {{3DM_tc23}}<br /> * {{Paralledge_tmc23}}<br /> * {{Joint_ton22}}<br /> * {{Towards_tmc22}}<br /> * {{edgebook}}<br /> * {{Resource_tii21}}<br /> * {{Perform_tmc21}}<br /> * {{Repeatable_ton20}}<br /> * {{Adaplora_icnp20}}<br /> * {{Channel_tii20}}<br /> * {{Towards_icdcs19}}<br /> * {{Lora_comst19}}<br /> * {{Perform_jsac19}}<br /> * {{Towards_infocom18}}<br /> * {{Accurate_tmc18}}<br /> * {{Embracing_tmc17}}<br /> * {{Accurate_ton17}}<br /> * {{Cormodel_infocom15}}<br /> ----<br /> <br /> ==Grants==<br /> * Integrated Sensing for Digital Twin Systems, National Natural Science Foundation of China (NSFC).<br /> * Data Management in Future UAV Networks, Sichuan Natural Science Foundation.<br /> * Reliable and Efficient Task Management in Edge Computing for AIoT Systems, MSCA Individual Fellowship.<br /> * Edge Network Deployment for Smart Cities, Sichuan Natural Science Foundation.<br /> * IPv6 Cyberspace Management, National Key Research and Development Program of China.<br /> * Study on Edge Computing for Urban Internet-of-Things, National Natural Science Foundation of China (NSFC).<br /> * QoE Optimization for Network Virtualization in Edge Computing, National Natural Science Foundation of China (NSFC).<br /> * Research on Crowd Intelligence, National Key Research and Development Program of China.<br /> * Study on Task Offloading in Low-power Edge-IoT Systems, China Postdoctoral Science Foundation.<br /> * Data Collection and Pre-Processing in Low-power and Heterogeneous Smart Healthcare Systems, the Fundamental Research Funds for the Central Universities.<br /> * Study on wireless link correlation: Modeling, Measurement and Applications, National Natural Science Foundation of China (NSFC).<br /> * Wireless dissemination protocols based on link correlation, Open research fundings of key laboratory of Zhejiang Province.<br /> <br /> ----<br /> ==Courses==<br /> * [Undergraduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [Undergraduate] [[Course:学术论文写作|Academic writing]]<br /> * [Undergraduate] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/toc.html Computer networks]<br /> * [Graduate] [[Course:Advanced_Network_Computing|Advanced Network Computing]]<br /> * [PhD] [https://webvpn.uestc.edu.cn/https/77726476706e69737468656265737421fdf952d232357b447d468aa2/pub_slides/ranc/ Network Computing]<br /> ----<br /> <br /> ==Professional activities==<br /> * &lt;b&gt;Program chair&lt;/b&gt;: IEEE ISCC 2017, IEEE IUCC 2023.<br /> * &lt;b&gt;Publication chair&lt;/b&gt;: IEEE IUCC 2021, IEEE ISPA 2020, IEEE HPCC 2018.<br /> * &lt;b&gt;TPC&lt;/b&gt;: IEEE ICPADS 2023, IEEE EDGE 2023, IEEE AIoTSys 2023, IEEE MSN 2023, IEEE ICC 2023, IEEE ICPADS 2022, IEEE SmartCity 2022, CCF CWSN 2022, IEEE ICPADS 2022, IEEE EDGE 2022, IEEE ICC 2021, IEEE CoWireless 2019, IEEE ICCCN 2019, ACM EWSN 2019, IEEE EWSN 2020, IEEE CSS 2017, IEEE DependSys 2017.<br /> * &lt;b&gt;Guest Editor&lt;/b&gt;: Electronics, IEEE OJ-COMS, Frontiers in Communications and Networks, Concurrency and Computation: Practice and Experience.<br /> * &lt;b&gt;Editorial board&lt;/b&gt;: International Journal on AdHoc Networking Systems.<br /> * &lt;b&gt;Workshop chair&lt;/b&gt;: The 2017 International Symposium on Advanced Topics in Computing Technology and Applications, The 2nd International Workshop on Mobile Social Networking and Computing (MSNCom-2017), The 4th International Workshop on Multi-access Edge Computing and Networking (MECN-2019).<br /> <br /> &lt;html&gt;<br /> &lt;!-- hitwebcounter Code START --&gt;<br /> &lt;script type=text/javascript id=clustrmaps src=//cdn.clustrmaps.com/map_v2.js?u=NkC4&amp;d=_X2HRNCM-hYnjCqX8EEEbJVR0hT-3LusML7fSP3jHo4&gt;&lt;/script&gt;<br /> &lt;/div&gt;<br /> &lt;/html&gt;</div>

Zhiwei http://mobinets.cn/site/index.php?title=Template:Gedes_eurosys26&diff=3429 2025-09-30T08:49:23Z

<p>Zhiwei: Created page with &quot;{{Pub |sn=EuroSys |authors=Q. Li, Z. Zhao*, G. Min, Z. Wang and L. Fu |link=https://mobinets.cn/ |title=GeDES: GPU-Driven Discrete Event Network Simulator |venue=ACM EuroSys |...&quot;</p> <hr /> <div>{{Pub<br /> |sn=EuroSys<br /> |authors=Q. Li, Z. Zhao*, G. Min, Z. Wang and L. Fu<br /> |link=https://mobinets.cn/<br /> |title=GeDES: GPU-Driven Discrete Event Network Simulator<br /> |venue=ACM EuroSys<br /> |year=2026<br /> }}<br /> <br /> [[Category:Papers]]</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3428 2025-09-25T13:23:16Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-09-25 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = Distributed Edge Computing (DEC) has emerged as a novel paradigm, owing to its superior performance in communication latency, parallel computing efficiency, and energy consumption. With the surge of tasks in generative artificial intelligence, DEC faces higher demands for parallel computing efficiency. Scheduling multiple tasks for simultaneous processing, rather than one-by-one handling, could enhance parallel efficiency. Multiple tasks have multi-dependencies, i.e., sequence dependency, attribute similarity, and attribute correlation. Utilizing the bidirectional edges of traditional graphs to represent multi-dependencies can lead to an explosion in quantity. A hypergraph, with its hyperedges capable of connecting any number of vertices, can significantly solve the above problem. However, the multi-dependencies are rarely studied in the current research, posing the challenges, including incapable representing and unable capturing of multi-dependency hypergraph. In this work, we introduce a Joint communication and computation scheduling for hypErgraph Tasks in DEC, namely HypeJet, To effectively represent multi-dependencies, we employ hypergraph construction to represent task attributes and utilize hypergraph partitioning to clarify and refine task attribute correlations, enhancing parallel efficiency. In response to the challenge of capturing multi-dependencies, we employ a scheduling mechanism with the hypergraph neural network that efficiently acquires higher-order attribute correlated information among convolution matrices, providing enriched contextual information on multi-dependencies that supports decision-making in scheduling tasks. The evaluations using real-world traces demonstrate an 18.07% improvement in parallel efficiency of task scheduling.<br /> |confname =INFOCOM'25<br /> |link = https://ieeexplore.ieee.org/abstract/document/11044587<br /> |title= HyperJet: Joint Communication and Computation Scheduling for Hypergraph Tasks in Distributed Edge Computing<br /> |speaker= Yi Zhou<br /> |date=2025-9-26<br /> }}{{Latest_seminar<br /> |abstract = Localization of networked nodes is an essential problem in emerging applications, including first-responder navigation, automated manufacturing lines, vehicular and drone navigation, asset tracking, Internet of Things, and 5G communication networks. In this paper, we present Locate3D, a novel system for peer-to-peer node localization and orientation estimation in large networks. Unlike traditional range-only methods, Locate3D introduces angle-of-arrival (AoA) data as an added network topology constraint. The system solves three key challenges: it uses angles to reduce the number of measurements required by 4× and jointly uses range and angle data for location estimation. We develop a spanning-tree approach for fast location updates, and to ensure the output graphs are rigid and uniquely realizable, even in occluded or weakly connected areas. Locate3D cuts down latency by up to 75% without compromising accuracy, surpassing standard range-only solutions. It has a 0.86 meter median localization error for building-scale multi-floor networks (32 nodes, 0 anchors) and 12.09 meters for large-scale networks (100,000 nodes, 15 anchors).<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/garg<br /> |title= Large Network UWB Localization: Algorithms and Implementation<br /> |speaker=Bangguo<br /> |date=2025-9-26<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3425 2025-09-18T10:03:47Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-09-19 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = With cloud-side computing and rendering, mobile cloud gaming (MCG) is expected to deliver high-quality gaming experiences to budget mobile devices. However, our measurement on representative MCG platforms reveals that even under good network conditions, all platforms exhibit high interactive latency of 112–403 ms, from a user-input action to its display response, that critically affects users’ quality of experience. Moreover, jitters in network latency often lead to significant fluctuations in interactive latency. In this work, we collaborate with a commercial MCG platform to conduct the first in-depth analysis on the interactive latency of cloud gaming. We identify VSync, the synchronization primitive of Android graphics pipeline, to be a key contributor to the excessive interactive latency; as many as five VSync events are intricately invoked, which serialize the complex graphics processing logic on both the client and cloud sides. To address this, we design an end-to-end VSync regulator, dubbed LoopTailor, which minimizes VSync events by decoupling game rendering from the lengthy cloud-side graphics pipeline and coordinating cloud game rendering directly with the client. We implement LoopTailor on the collaborated platform and commodity Android devices, reducing the interactive latency (by ∼34%) to stably below 100 ms.<br /> |confname =NSDI'25<br /> |link = https://www.usenix.org/conference/nsdi25/presentation/li-yang<br /> |title= Dissecting and Streamlining the Interactive Loop of Mobile Cloud Gaming<br /> |speaker= Li Chen<br /> |date=2025-9-9<br /> }}<br /> {{Latest_seminar<br /> |abstract = The local deployment of large language models (LLMs) on mobile devices has garnered increasing attention due to its advantages in enhancing user privacy and enabling offline operation. However, given the limited computational resources of a single mobile device, only small language models (SLMs) with restricted capabilities can currently be supported. In this paper, we explore the potential of leveraging the collective computing power of multiple mobile devices to collaboratively support more efficient local LLM inference. We evaluate the feasibility and efficiency of existing parallelism techniques under the constraints of mobile devices and wireless network, identifying that chunked pipeline parallelism holds promise for realizing this vision. Building on this insight, we propose FlexSpark, a novel solution designed to achieve efficient and robust multi-device collaborative inference. FlexSpark incorporates priority scheduling, ordered communication, and elastic compression to maximize wireless bandwidth utilization, and thus accelerates distributed inference. Preliminary experimental results demonstrate that FlexSpark achieves up to a 2 × speedup compared to state-of-the-art frameworks, significantly enhancing the practicality and scalability of LLM deployment on mobile devices.<br /> |confname =APNet'25<br /> |link = https://dl.acm.org/doi/10.1145/3735358.3735368<br /> |title= FlexSpark: Robust and Efficient Multi-Device Collaborative Inference over Wireless Network<br /> |speaker=Ruizhen<br /> |date=2025-9-19<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Seminar&diff=3422 2025-09-12T03:25:35Z

<p>Zhiwei: </p> <hr /> <div>{{SemNote<br /> |time='''2025-09-12 10:30'''<br /> |addr=4th Research Building A518<br /> |note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].<br /> }}<br /> <br /> ===Latest===<br /> <br /> {{Latest_seminar<br /> |abstract = Reconfigurable Intelligent Surfaces (RIS) are a promising technology for creating smart radio environments by controlling wireless propagation. However, several factors hinder the integration of RIS technology into existing cellular networks, including the incompatibility of RIS control interfaces with 5G PHY/MAC procedures for synchronizing radio scheduling decisions and RIS operation, and the cost and energy limitations of passive RIS technology. This paper presents RISENSE, a system for practical RIS integration in cellular networks. First, we propose a novel, low-cost, and low-power RIS design capable of decoding control messages without complex baseband operations or additional RF chains, utilizing a power sensor and a network of microstrip lines and couplers. Second, we design an effective in-band wireless RIS control interface, compatible with 5G PHY/MAC procedures, that embeds amplitude-modulated (AM) RIS control commands directly into standard OFDM-modulated 5G data channels. Finally, we propose a low-overhead protocol that supports swift on-demand RIS re-con gurability, making it adaptable to varying channel conditions and user mobility, while minimizing the wastage of 5G OFDM symbols. Our experiments validate the design of RISENSE and our evaluation shows that our system can reconfigure a RIS at the same pace as users move, boosting 5G coverage where static or slow RIS controllers cannot.<br /> |confname = Mobisys'25<br /> |link = https://dspace.networks.imdea.org/handle/20.500.12761/1925<br /> |title= RISENSE: Long-Range In-Band Wireless Control of Passive Reconfigurable Intelligent Surfaces<br /> |speaker= Haifeng<br /> |date=2025-9-12<br /> }}<br /> {{Latest_seminar<br /> |abstract = Traditional 3D content representations include dense point clouds that consume large amounts of data and hence network bandwidth, while newer representations such as neural radiance fields suffer from poor frame rates due to their non-standard volumetric rendering pipeline. 3D Gaussian splats (3DGS) can be seen as a generalization of point clouds that meet the best of both worlds, with high visual quality and efficient rendering for real-time frame rates. However, delivering 3DGS scenes from a hosting server to client devices is still challenging due to high network data consumption (e.g., 1.5 GB for a single scene). The goal of this work is to create an efficient 3D content delivery framework that allows users to view high quality 3D scenes with 3DGS as the underlying data representation. The main contributions of the paper are: (1) Creating new layered 3DGS scenes for efficient delivery, (2) Scheduling algorithms to choose what splats to download at what time, and (3) Trace-driven experiments from users wearing virtual reality headsets to evaluate the visual quality and latency. Our system for Layered 3D Gaussian Splats delivery (L3GS) demonstrates high visual quality, achieving 16.9% higher average SSIM compared to baselines, and also works with other compressed 3DGS representations. The code is available at https://github.com/mavens-lab/layered_3d_gaussian_splats.<br /> |confname =Mobicom'25<br /> |link = https://arxiv.org/html/2504.05517v1<br /> |title= L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery<br /> |speaker=Jiyi<br /> |date=2025-9-12<br /> }}<br /> {{Resource:Previous_Seminars}}</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Paper_Carnival_2025&diff=3417 2025-08-27T14:51:52Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=Carnival 2025<br /> |content=<br /> :'''Time''': 2025-08-27 ~ 2025-08-28<br /> :'''Location''': A518<br /> }}<br /> == '''Day 1''' ==<br /> ==='''Session 1''': Networked System===<br /> ====1. LLM Cache Optimization - Qinyong Li &quot;9:00-9:40&quot; ====<br /> * [Eurosys'25] [https://arxiv.org/pdf/2405.16444 CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion]<br /> * [SigComm'24] [https://dl.acm.org/doi/pdf/10.1145/3651890.3672274 CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving]<br /> <br /> ====2. Disaggregated OS - Haifeng &quot;9:40-10:00&quot;====<br /> * [NSDI'25] [https://www.usenix.org/system/files/nsdi25-li-quanxi.pdf Beehive: A Scalable Disaggregated Memory Runtime Exploiting Asynchrony of Multithreaded Programs]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> ==='''Session 2''': Video Analytics for AIoT ===<br /> ====1. ML for VA - Xinyan &quot;10:05-10:45&quot;====<br /> * [ISCA'24] [https://ieeexplore.ieee.org/document/10609643 DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics]<br /> * [NSDI'23] [https://www.usenix.org/system/files/nsdi23-khani.pdf RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics]<br /> * [MM'23] [https://arxiv.org/pdf/2308.16413 Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments]<br /> ====2. Image Offloading Revisit - Yi Zhou &quot;10:45-11:05&quot;====<br /> * [MobiSys 2024] [https://arxiv.org/pdf/2504.13736 LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices]<br /> ====3. Vision Drones - Jiahao &quot;11:05-11:25&quot;====<br /> * [T-RO'25] [https://ieeexplore.ieee.org/abstract/document/10816005 FAPP: Fast and Adaptive Perception and Planning for UAVs in Dynamic Cluttered Environments]<br /> <br /> ===Break &quot;11:25-14:00&quot;===<br /> ----<br /> === '''Session 3''': Networking ===<br /> ====1. Quantum Networks - Yaliang &quot;14:00-14:40&quot;====<br /> * [INFOCOM'22] [http://staff.ustc.edu.cn/~zgm1993/papers/2022+INFOCOM+E2E%20Fidelity%20Aware%20Routing%20and%20Purification%20for%20Throughput%20Maximization%20in%20Quantum%20Networks.pdf E2E Fidelity Aware Routing and Purification for Throughput Maximization in Quantum Networks]<br /> * [JSAC'24] [https://ieeexplore.ieee.org/abstract/document/10477477 On Optimum Entanglement Purification Scheduling in Quantum Networks]<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044462 Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks]<br /> ====2. V2V Networks - Zhenguo Bi &quot;14:40-15:00&quot;====<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044682 RoCooper: Robust Cooperative Perception under Vehicle-to-Vehicle Communication Impairments]<br /> === Break &quot;15:00-15:05&quot; ===<br /> ----<br /> === '''Session 4''': LoRa ===<br /> ====1. ML in LoRa Reception - Kai Chen&quot;15:05-15:45&quot;====<br /> * [ICNP'23] [https://ieeexplore.ieee.org/abstract/document/10355583 Hi&lt;sup&gt;2&lt;/sup&gt;LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost]<br /> * [SenSys'24] [https://dl.acm.org/doi/10.1145/3666025.3699354 Enhancing LoRa Reception with Generative Models: Channel-Aware Denoising of LoRaPHY Signals]<br /> * [ICNP'24] [https://ieeexplore.ieee.org/document/10858555 Deepdetangle: Deep Learning-Based Fusion of Chirp-Level and Packet-Level Features for Lora Parallel Decoding]<br /> ====2. Performance - Mengyu &quot;15:45-16:15&quot;====<br /> * [ToN'24] [https://ieeexplore.ieee.org/document/10507855 RALoRa: Rateless-Enabled Link Adaptation for LoRa Networking]<br /> * [TMC'25] [https://ieeexplore.ieee.org/document/11080118 Enhancing Link Performance for Mobile LoRa Networks]<br /> <br /> === Break &quot;16:15-16:20&quot; ===<br /> ----<br /> === '''Session 5''': LLM Code Generation ===<br /> ====1. Use of CodeGen - Youwei &quot;16:20-16:40&quot;====<br /> * [Mobicom'25] [https://arxiv.org/pdf/2412.18116 AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation]<br /> ====2. Code Translation - Bairong &quot;16:40-17:00&quot;====<br /> * [ICSE'25] [https://arxiv.org/abs/2411.01063 InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation]<br /> * [Arxiv] [https://arxiv.org/abs/2503.05346 AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications]<br /> <br /> ----<br /> <br /> == '''Day 2''' ==<br /> ==='''Session 6''': Volumetric video===<br /> ====1.Volume Video- Mengfan &quot;9:00-9:20&quot;====<br /> * [Mobicom'24] [https://dl.acm.org/doi/abs/10.1145/3636534.3690685 An End-to-End, Low-Cost, and High-Fidelity 3D Video Pipeline for Mobile Devices]<br /> ====2.Volume Video- Jiyi &quot;9:20-10:00&quot;====<br /> * [TOG'23] [https://scholar.google.com/scholar?hl=en&amp;as_sdt=0%2C5&amp;q=Gaussian+Splatting+for+Real-Time+Radiance+Field+Rendering&amp;btnG= 3D Gaussian Splatting for Real-Time Radiance Field Rendering]<br /> * [TOG'24] [https://dl.acm.org/doi/pdf/10.1145/3687935 V&lt;sup&gt;3&lt;/sup&gt;: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> === '''Session 7''': Edge Deployment and Inference===<br /> ====1. Edge LLM - Junzhe &quot;10:05-10:25&quot;====<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/document/11044447 TensAllo: Adaptive Deployment of LLMs on Resource-Constrained Heterogeneous Edge Devices]<br /> ====2. Inference Optimization - Ruizheng &quot;10:25-10:45&quot;====<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044678 DUNE: Distributed Inference in the User Plane]<br /> ----<br /> <br /> === '''Session 8''': Summary and closing remarks ===</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Paper_Carnival_2025&diff=3416 2025-08-27T07:59:02Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=Carnival 2025<br /> |content=<br /> :'''Time''': 2025-08-27 ~ 2025-08-28<br /> :'''Location''': A518<br /> }}<br /> == '''Day 1''' ==<br /> ==='''Session 1''': Networked System===<br /> ===1. LLM Cache Optimization - Qinyong Li &quot;9:00-9:40&quot; ===<br /> * [Eurosys'25] [https://arxiv.org/pdf/2405.16444 CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion]<br /> * [SigComm'24] [https://dl.acm.org/doi/pdf/10.1145/3651890.3672274 CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving]<br /> <br /> ===2. Disaggregated OS - Haifeng &quot;9:40-10:00&quot;===<br /> * [NSDI'25] [https://www.usenix.org/system/files/nsdi25-li-quanxi.pdf Beehive: A Scalable Disaggregated Memory Runtime Exploiting Asynchrony of Multithreaded Programs]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> ==='''Session 2''': Video Analytics for AIoT ===<br /> ===1. ML for VA - Xinyan &quot;10:05-10:45&quot;===<br /> * [ISCA'24] [https://ieeexplore.ieee.org/document/10609643 DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics]<br /> * [NSDI'23] [https://www.usenix.org/system/files/nsdi23-khani.pdf RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics]<br /> * [MM'23] [https://arxiv.org/pdf/2308.16413 Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments]<br /> ===2. Image Offloading Revisit - Yi Zhou &quot;10:45-11:05&quot;===<br /> * [MobiSys 2024] [https://arxiv.org/pdf/2504.13736 LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices]<br /> ===3. Vision Drones - Jiahao &quot;11:05-11:25&quot;===<br /> * [T-RO'25] [https://ieeexplore.ieee.org/abstract/document/10816005 FAPP: Fast and Adaptive Perception and Planning for UAVs in Dynamic Cluttered Environments]<br /> <br /> ===Break &quot;11:25-14:00&quot;===<br /> ----<br /> === '''Session 3''': Networking ===<br /> ===1. Quantum Networks - Yaliang &quot;14:00-14:40&quot;===<br /> * [INFOCOM'22] [http://staff.ustc.edu.cn/~zgm1993/papers/2022+INFOCOM+E2E%20Fidelity%20Aware%20Routing%20and%20Purification%20for%20Throughput%20Maximization%20in%20Quantum%20Networks.pdf E2E Fidelity Aware Routing and Purification for Throughput Maximization in Quantum Networks]<br /> * [JSAC'24] [https://ieeexplore.ieee.org/abstract/document/10477477 On Optimum Entanglement Purification Scheduling in Quantum Networks]<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044462 Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks]<br /> ===2. V2V Networks - Zhenguo Bi &quot;14:40-15:00&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044682 RoCooper: Robust Cooperative Perception under Vehicle-to-Vehicle Communication Impairments]<br /> === Break &quot;15:00-15:05&quot; ===<br /> ----<br /> === '''Session 4''': LoRa ===<br /> ===1. ML in LoRa Reception - Kai Chen&quot;15:05-15:45&quot;===<br /> * [ICNP'23] [https://ieeexplore.ieee.org/abstract/document/10355583 Hi&lt;sup&gt;2&lt;/sup&gt;LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost]<br /> * [SenSys'24] [https://dl.acm.org/doi/10.1145/3666025.3699354 Enhancing LoRa Reception with Generative Models: Channel-Aware Denoising of LoRaPHY Signals]<br /> * [ICNP'24] [https://ieeexplore.ieee.org/document/10858555 Deepdetangle: Deep Learning-Based Fusion of Chirp-Level and Packet-Level Features for Lora Parallel Decoding]<br /> ===2. Performance - Mengyu &quot;15:45-16:15&quot;===<br /> * [ToN'24] [https://ieeexplore.ieee.org/document/10507855 RALoRa: Rateless-Enabled Link Adaptation for LoRa Networking]<br /> * [TMC'25] [https://ieeexplore.ieee.org/document/11080118 Enhancing Link Performance for Mobile LoRa Networks]<br /> <br /> === Break &quot;16:15-16:20&quot; ===<br /> ----<br /> === '''Session 5''': LLM Code Generation ===<br /> ===1. Use of CodeGen - Youwei &quot;16:20-16:40&quot;===<br /> * [Mobicom'25] [https://arxiv.org/pdf/2412.18116 AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation]<br /> ===2. Code Translation - Bairong &quot;16:40-17:00&quot;===<br /> * [ICSE'25] [https://arxiv.org/abs/2411.01063 InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation]<br /> * [Arxiv] [https://arxiv.org/abs/2503.05346 AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications]<br /> <br /> ----<br /> <br /> == '''Day 2''' ==<br /> ==='''Session 6''': Volumetric video===<br /> ===1.Volume Video- Mengfan &quot;9:00-9:20&quot;===<br /> * [Mobicom'24] [https://dl.acm.org/doi/abs/10.1145/3636534.3690685 An End-to-End, Low-Cost, and High-Fidelity 3D Video Pipeline for Mobile Devices]<br /> ===2.Volume Video- Jiyi &quot;9:20-10:00&quot;===<br /> * [TOG'23] [https://scholar.google.com/scholar?hl=en&amp;as_sdt=0%2C5&amp;q=Gaussian+Splatting+for+Real-Time+Radiance+Field+Rendering&amp;btnG= 3D Gaussian Splatting for Real-Time Radiance Field Rendering]<br /> * [TOG'24] [https://dl.acm.org/doi/pdf/10.1145/3687935 V&lt;sup&gt;3&lt;/sup&gt;: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> === '''Session 7''': Edge Deployment and Inference===<br /> ===1. Edge LLM - Junzhe &quot;10:05-10:25&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/document/11044447 TensAllo: Adaptive Deployment of LLMs on Resource-Constrained Heterogeneous Edge Devices]<br /> ===2. Inference Optimization - Ruizheng &quot;10:25-10:45&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044678 DUNE: Distributed Inference in the User Plane]<br /> ----<br /> <br /> === '''Session 8''': Summary and closing remarks ===</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Paper_Carnival_2025&diff=3415 2025-08-27T07:56:23Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=Carnival 2025<br /> |content=<br /> :'''Time''': 2025-08-27 ~ 2025-08-28<br /> :'''Location''': A518<br /> }}<br /> == '''Day 1''' ==<br /> ==='''Session 1''': Networked System===<br /> ===1. LLM Cache Optimization - Qinyong Li &quot;9:00-9:40&quot; ===<br /> * [Eurosys'25] [https://arxiv.org/pdf/2405.16444 CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion]<br /> * [SigComm'24] [https://dl.acm.org/doi/pdf/10.1145/3651890.3672274 CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving]<br /> <br /> ===2. Disaggregated OS - Haifeng &quot;9:40-10:00&quot;===<br /> * [NSDI'25] [https://www.usenix.org/system/files/nsdi25-li-quanxi.pdf Beehive: A Scalable Disaggregated Memory Runtime Exploiting Asynchrony of Multithreaded Programs]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> ==='''Session 2''': Video Analytics for AIoT ===<br /> ===1. ML for VA - Xinyan &quot;10:05-10:45&quot;===<br /> * [ISCA'24] [https://ieeexplore.ieee.org/document/10609643 DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics]<br /> * [NSDI'23] [https://www.usenix.org/system/files/nsdi23-khani.pdf RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics]<br /> * [MM'23] [https://arxiv.org/pdf/2308.16413 Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments]<br /> ===2. Image Offloading Revisit - Yi Zhou &quot;10:45-11:05&quot;===<br /> * [MobiSys 2024] [https://arxiv.org/pdf/2504.13736 LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices]<br /> ===3. Vision Drones - Jiahao &quot;11:05-11:25&quot;===<br /> * [T-RO'25] [https://ieeexplore.ieee.org/abstract/document/10816005 FAPP: Fast and Adaptive Perception and Planning for UAVs in Dynamic Cluttered Environments]<br /> <br /> ===Break &quot;11:25-14:00&quot;===<br /> ----<br /> === '''Session 3''': Networking ===<br /> ===1. Quantum Networks - Yaliang &quot;14:00-14:40&quot;===<br /> * [INFOCOM'22] [http://staff.ustc.edu.cn/~zgm1993/papers/2022+INFOCOM+E2E%20Fidelity%20Aware%20Routing%20and%20Purification%20for%20Throughput%20Maximization%20in%20Quantum%20Networks.pdf E2E Fidelity Aware Routing and Purification for Throughput Maximization in Quantum Networks]<br /> * [JSAC'24] [https://ieeexplore.ieee.org/abstract/document/10477477 On Optimum Entanglement Purification Scheduling in Quantum Networks]<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044462 Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks]<br /> ===2. V2V Networks - Zhenguo Bi &quot;14:40-15:00&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044682 RoCooper: Robust Cooperative Perception under Vehicle-to-Vehicle Communication Impairments]<br /> === Break &quot;15:00-15:05&quot; ===<br /> ----<br /> === '''Session 4''': LoRa ===<br /> ===1. ML in LoRa Reception - Kai Chen&quot;15:05-15:45&quot;===<br /> * [ICNP'23] [https://ieeexplore.ieee.org/abstract/document/10355583 Hi&lt;sup&gt;2&lt;/sup&gt;LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost]<br /> * [SenSys'24] [https://dl.acm.org/doi/10.1145/3666025.3699354 Enhancing LoRa Reception with Generative Models: Channel-Aware Denoising of LoRaPHY Signals]<br /> * [ICNP'24] [https://ieeexplore.ieee.org/document/10858555 Deepdetangle: Deep Learning-Based Fusion of Chirp-Level and Packet-Level Features for Lora Parallel Decoding]<br /> ===2. Performance - Mengyu &quot;15:45-16:15&quot;===<br /> * [ToN'24] [https://ieeexplore.ieee.org/document/10507855 RALoRa: Rateless-Enabled Link Adaptation for LoRa Networking]<br /> * [TMC'25] [https://ieeexplore.ieee.org/document/11080118 Enhancing Link Performance for Mobile LoRa Networks]<br /> <br /> === Break &quot;16:15-16:20&quot; ===<br /> ----<br /> === '''Session 5''': LLM Code Generation ===<br /> ===Use of CodeGen - Youwei &quot;16:20-16:40&quot;===<br /> * [Mobicom'25] [https://arxiv.org/pdf/2412.18116 AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation]<br /> ===Code Translation - Bairong &quot;16:40-17:00&quot;===<br /> * [ICSE'25] [https://arxiv.org/abs/2411.01063 InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation]<br /> * [Arxiv] [https://arxiv.org/abs/2503.05346 AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications]<br /> <br /> ----<br /> <br /> == '''Day 2''' ==<br /> ==='''Session 6''': Volumetric video===<br /> ===1.Volume Video- Mengfan &quot;9:00-9:20&quot;===<br /> * [Mobicom'24] [https://dl.acm.org/doi/abs/10.1145/3636534.3690685 An End-to-End, Low-Cost, and High-Fidelity 3D Video Pipeline for Mobile Devices]<br /> ===2.Volume Video- Jiyi &quot;9:20-10:00&quot;===<br /> * [TOG'23] [https://scholar.google.com/scholar?hl=en&amp;as_sdt=0%2C5&amp;q=Gaussian+Splatting+for+Real-Time+Radiance+Field+Rendering&amp;btnG= 3D Gaussian Splatting for Real-Time Radiance Field Rendering]<br /> * [TOG'24] [https://dl.acm.org/doi/pdf/10.1145/3687935 V&lt;sup&gt;3&lt;/sup&gt;: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> === '''Session 7''': Edge Deployment and Inference===<br /> ===1. Edge LLM - Junzhe &quot;10:05-10:25&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/document/11044447 TensAllo: Adaptive Deployment of LLMs on Resource-Constrained Heterogeneous Edge Devices]<br /> ===2. Inference Optimization - Ruizheng &quot;10:25-10:45&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044678 DUNE: Distributed Inference in the User Plane]<br /> ----<br /> <br /> === '''Session 8''': Summary and closing remarks ===</div>

Zhiwei http://mobinets.cn/site/index.php?title=Resource:Paper_Carnival_2025&diff=3414 2025-08-27T03:39:29Z

<p>Zhiwei: </p> <hr /> <div>{{Tip<br /> |title=Carnival 2025<br /> |content=<br /> :'''Time''': 2025-08-27 ~ 2025-08-28<br /> :'''Location''': A518<br /> }}<br /> == '''Day 1''' ==<br /> ==='''Session 1''': Networked System===<br /> ===1. LLM Cache Optimization - Qinyong Li &quot;9:00-9:40&quot; ===<br /> * [Eurosys'25] [https://arxiv.org/pdf/2405.16444 CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion]<br /> * [SigComm'24] [https://dl.acm.org/doi/pdf/10.1145/3651890.3672274 CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving]<br /> <br /> ===2. Disaggregated OS - Haifeng &quot;9:40-10:00&quot;===<br /> * [NSDI'25] [https://www.usenix.org/system/files/nsdi25-li-quanxi.pdf Beehive: A Scalable Disaggregated Memory Runtime Exploiting Asynchrony of Multithreaded Programs]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> ==='''Session 2''': Video Analytics for AIoT ===<br /> ===1. ML for VA - Xinyan &quot;10:05-10:45&quot;===<br /> * [ISCA'24] [https://ieeexplore.ieee.org/document/10609643 DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics]<br /> * [NSDI'23] [https://www.usenix.org/system/files/nsdi23-khani.pdf RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics]<br /> * [MM'23] [https://arxiv.org/pdf/2308.16413 Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments]<br /> ===2. Image Offloading Revisit - Yi Zhou &quot;10:45-11:05&quot;===<br /> * [MobiSys 2024] [https://arxiv.org/pdf/2504.13736 LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices]<br /> ===3. Vision Drones - Jiahao &quot;11:05-11:25&quot;===<br /> * [T-RO'25] [https://ieeexplore.ieee.org/abstract/document/10816005 FAPP: Fast and Adaptive Perception and Planning for UAVs in Dynamic Cluttered Environments]<br /> <br /> ===Break &quot;11:25-14:00&quot;===<br /> ----<br /> === '''Session 3''': Networking ===<br /> ===1. Quantum Networks - Yaliang &quot;14:00-14:40&quot;===<br /> * [INFOCOM'22] [http://staff.ustc.edu.cn/~zgm1993/papers/2022+INFOCOM+E2E%20Fidelity%20Aware%20Routing%20and%20Purification%20for%20Throughput%20Maximization%20in%20Quantum%20Networks.pdf E2E Fidelity Aware Routing and Purification for Throughput Maximization in Quantum Networks]<br /> * [JSAC'24] [https://ieeexplore.ieee.org/abstract/document/10477477 On Optimum Entanglement Purification Scheduling in Quantum Networks]<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044462 Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks]<br /> ===2. V2V Networks - Zhenguo Bi &quot;14:40-15:00&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044682 RoCooper: Robust Cooperative Perception under Vehicle-to-Vehicle Communication Impairments]<br /> === Break &quot;15:00-15:05&quot; ===<br /> ----<br /> === '''Session 4''': LoRa ===<br /> ===1. ML in LoRa Reception - Kai Chen&quot;15:05-15:45&quot;===<br /> * [ICNP'23] [https://ieeexplore.ieee.org/abstract/document/10355583 Hi2LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost]<br /> * [SenSys'24] [https://dl.acm.org/doi/10.1145/3666025.3699354 Enhancing LoRa Reception with Generative Models: Channel-Aware Denoising of LoRaPHY Signals]<br /> * [ICNP'24] [https://ieeexplore.ieee.org/document/10858555 Deepdetangle: Deep Learning-Based Fusion of Chirp-Level and Packet-Level Features for Lora Parallel Decoding]<br /> ===2. Performance - Mengyu &quot;15:45-16:15&quot;===<br /> * [ToN'24] [https://ieeexplore.ieee.org/document/10507855 RALoRa: Rateless-Enabled Link Adaptation for LoRa Networking]<br /> * [TMC'25] [https://ieeexplore.ieee.org/document/11080118 Enhancing Link Performance for Mobile LoRa Networks]<br /> <br /> === Break &quot;16:15-16:20&quot; ===<br /> ----<br /> === '''Session 5''': LLM Code Generation ===<br /> ===Use of CodeGen - Youwei &quot;16:20-16:40&quot;===<br /> * [Mobicom'25] [https://arxiv.org/pdf/2412.18116 AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation]<br /> ===Code Translation - Bairong &quot;16:40-17:00&quot;===<br /> * [ICSE'25] [https://arxiv.org/abs/2411.01063 InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation]<br /> * [Arxiv] [https://arxiv.org/abs/2503.05346 AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications]<br /> <br /> ----<br /> <br /> == '''Day 2''' ==<br /> ==='''Session 6''': Volumetric video===<br /> ===1.Volume Video- Mengfan &quot;9:00-9:20&quot;===<br /> * [Mobicom'24] [https://dl.acm.org/doi/abs/10.1145/3636534.3690685 An End-to-End, Low-Cost, and High-Fidelity 3D Video Pipeline for Mobile Devices]<br /> ===2.Volume Video- Jiyi &quot;9:20-10:00&quot;===<br /> * [TOG'23] [https://scholar.google.com/scholar?hl=en&amp;as_sdt=0%2C5&amp;q=Gaussian+Splatting+for+Real-Time+Radiance+Field+Rendering&amp;btnG= 3D Gaussian Splatting for Real-Time Radiance Field Rendering]<br /> * [TOG'24] [https://dl.acm.org/doi/pdf/10.1145/3687935 V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians]<br /> ===Break &quot;10:00-10:05&quot;===<br /> ----<br /> === '''Session 7''': Edge Deployment and Inference===<br /> ===1. Edge LLM - Junzhe &quot;10:05-10:25&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/document/11044447 TensAllo: Adaptive Deployment of LLMs on Resource-Constrained Heterogeneous Edge Devices]<br /> ===2. Inference Optimization - Ruizheng &quot;10:25-10:45&quot;===<br /> * [INFOCOM'25] [https://ieeexplore.ieee.org/abstract/document/11044678 DUNE: Distributed Inference in the User Plane]<br /> ----<br /> <br /> === '''Session 8''': Summary and closing remarks ===</div>

Zhiwei