Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
 
(195 intermediate revisions by 6 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2022-6-27 10:30'''
|time='''2025-12-12 10:30'''
|addr=4th Research Building A527-B
|addr=4th Research Building A518
|note=Useful links: [[Resource:Reading_List|Readling list]]; [[Resource:Seminar_schedules|Schedules]]; [[Resource:Previous_Seminars|Previous seminars]].
|note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].
}}
}}


===Latest===
===Latest===
{{Latest_seminar
|abstract = Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code, which results in unguaranteed code executability and unreliable automated code translation. To address this issue, we propose ExeCoder, an LLM specifically designed for code translation, aimed at utilizing executability representations such as functional semantics, syntax structures, and variable dependencies to enhance the capabilities of LLMs in code translation. To evaluate the effectiveness of ExeCoder, we manually enhanced the widely used benchmark TransCoder-test, resulting in a benchmark called TransCoder-test-X that serves LLMs. Evaluation of TransCoder-test-X indicates that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics, and even outperforms the renowned closed-source LLM GPT-4o.
|confname =EMNLP'25
|link = https://arxiv.org/abs/2501.18460
|title= ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
|speaker=Youwei Ran
|date=2025-12-12
}}
{{Latest_seminar
{{Latest_seminar
|abstract = Recent advances in network and mobile computing.  
|abstract =Imitation learning from human demonstrations has shown impressive performance in robotics. However, most results focus on table-top manipulation, lacking the mobility and dexterity necessary for generally useful tasks. In this work, we develop a system for imitating mobile manipulation tasks that are bimanual and require whole-body control. We first present Mobile ALOHA, a low-cost and whole-body teleoperation system for data collection. It augments the ALOHA system with a mobile base, and a whole-body teleoperation interface. Using data collected with Mobile ALOHA, we then perform supervised behavior cloning and find that co-training with existing static ALOHA datasets boosts performance on mobile manipulation tasks. With 50 demonstrations for each task, co-training can increase success rates by up to 90%, allowing Mobile ALOHA to autonomously complete complex mobile manipulation tasks such as sauteing and serving a piece of shrimp, opening a two-door wall cabinet to store heavy cooking pots, calling and entering an elevator, and lightly rinsing a used pan using a kitchen faucet. We will open-source all the hardware and software implementations upon publication.
|confname=talk
|confname =CoRL'24
|link=[Resource:Paper Carnival 2022|Paper Carnival 2022
|link = https://openreview.net/forum?id=FO6tePGRZj
|title=]
|title= Mobile ALOHA: Learning Bimanual Mobile Manipulation using Low-Cost Whole-Body Teleoperation
|speaker=all
|speaker=Yi Zhou
 
|date=2025-12-12
 
 
}}
}}
'''Visible Light Communication--Wenliang'''
[Sensys 2021] [https://dl.acm.org/doi/pdf/10.1145/3485730.3485934 CurveLight: An Accurate and Practical Indoor Positioning System]
[Sensys 2021] [https://dl.acm.org/doi/pdf/10.1145/3485730.3485948 SpiderWeb: Enabling Through-Screen Visible Light Communication]
[Kaiwen][ICNP2022] [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9155474 X-MAC: Achieving High Scalability via Imperfect-Orthogonality Aware Scheduling in LPWAN]
'''Response to Mobility--Luwei'''
[Infocom2022] [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796811 Enabling QoE Support for Interactive Applications over Mobile Edge with High User Mobility]
[Infocom2022] [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796968 User Experience Oriented Task Computation for UAV-Assisted MEC System]
[TMC2022] [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9343712 ECHO: Efficient Zero-Control-Packet Broadcasting for Mobile Ad Hoc Networks]
[Zhuoliu][MobiCom21] [https://www.microsoft.com/en-us/research/uploads/prod/2021/09/Visage_Mobicom_2021.pdf Visage: enabling timely analytics for drone imagery]
'''Offloading, Delivery--Wenjie'''
[Infocom2022] [https://ieeexplore.ieee.org/document/9796843 An Efficient Two-Layer Task Offloading Scheme for MEC Networks with Multiple Services Providers]
[Infocom2022] [https://ieeexplore.ieee.org/document/9796714/ Two Time-Scale Joint Service Caching and Task Offloading for UAV-assisted Mobile Edge Computing]
[Infocom2022] [https://ieeexplore.ieee.org/document/9796763/ AoDNN: An Auto-Offloading Approach to Optimize Deep Inference for Fostering Mobile Web]
[TMC2022] [https://ieeexplore.ieee.org/document/9238459 A Force-Directed Approach to Seeking Route Recommendation in Ride-on-Demand Service Using Multi-Source Urban Data]
[Xinyu][INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796908/ IoTMosaic: Inferring User Activities from IoT Network Traffic in Smart Homes]
[Jiajun][INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796661/ Kalmia: A Heterogeneous QoS-aware Scheduling Framework for DNN Tasks on Edge Servers]
'''Video Service in Edge Networks--Congrong'''
[SigComm 2022] [https://dl.acm.org/doi/pdf/10.1145/3544216.3544218 NeuroScaler: neural video enhancement at scale]
[INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796984/ FlexPatch: Fast and Accurate Object Detection for On-device High-Resolution Live Video Analytics]
[INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796657/ DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation]
[MobiHoc 2021] [https://dl.acm.org/doi/pdf/10.1145/3466772.3467034 Task Offloading with Uncertain Processing Cycles]
'''Edge, offloading, caching--Qingyong'''
[Infocom 2022] [https://ieeexplore.ieee.org/document/9796969/ Online File Caching in Latency-Sensitive Systems with Delayed Hits and Bypassing]
[Infocom 2022] [https://dl.acm.org/doi/10.1109/INFOCOM48880.2022.9796799 Distributed Cooperative Caching in Unreliable Edge Environments]
[TMC 2022] [https://ieeexplore.ieee.org/abstract/document/9832640 Reverse Auction-based Computation Offloading and Resource Allocation in Mobile Cloud-Edge Computing]
[YuanQi][NSDI 2022] [https://www.microsoft.com/en-us/research/uploads/prod/2021/07/nsdi22spring-final74.pdf Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers]
[Wangkun][Infocom 2022][https://ieeexplore.ieee.org/document/9796884/ Joint Resource Management and Flow Scheduling for SFC Deployment in Hybrid Edge-and-Cloud Network]
'''Communication-Efficient Federated Learning--Jianqi'''
[ICML 2022] [https://arxiv.org/pdf/2111.00465.pdf DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning]
[ICML 2022] [https://proceedings.mlr.press/v162/yi22a/yi22a.pdf QSFL: A Two-Level Uplink Communication Optimization Framework for Federated Learning]
[INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796982/ Optimal Rate Adaption in Federated Learning with Compressed Communications]
'''Crowdsensing-Xianyang'''
[INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796960/ Learning for Crowdsourcing: Online Dispatch for Video Analytics with Guarantee]
[INFOCOM 2022] [https://ieeexplore.ieee.org/document/9796743/ Worker Selection Towards Data Completion for Online Sparse Crowdsensing]
[IoTJ] [https://ieeexplore.ieee.org/document/9828398/ Nondeterministic Mobility based Incentive Mechanism for Efficient Data Collection in Crowdsensing]
[Jiangshu][SIGCOMM2022] [https://dl.acm.org/doi/pdf/10.1145/3544216.3544238 From Luna to Solar: The Evolutions of the Compute-to-Storage Networks in Alibaba Cloud]
=== History ===
{{Resource:Previous_Seminars}}
{{Resource:Previous_Seminars}}

Latest revision as of 23:32, 11 December 2025

Time: 2025-12-12 10:30
Address: 4th Research Building A518
Useful links: 📚 Readling list; 📆 Schedules; 🧐 Previous seminars.

Latest

  1. [EMNLP'25] ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation, Youwei Ran
    Abstract: Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models (LLMs) for code translation. However, existing LLMs only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code, which results in unguaranteed code executability and unreliable automated code translation. To address this issue, we propose ExeCoder, an LLM specifically designed for code translation, aimed at utilizing executability representations such as functional semantics, syntax structures, and variable dependencies to enhance the capabilities of LLMs in code translation. To evaluate the effectiveness of ExeCoder, we manually enhanced the widely used benchmark TransCoder-test, resulting in a benchmark called TransCoder-test-X that serves LLMs. Evaluation of TransCoder-test-X indicates that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics, and even outperforms the renowned closed-source LLM GPT-4o.
  2. [CoRL'24] Mobile ALOHA: Learning Bimanual Mobile Manipulation using Low-Cost Whole-Body Teleoperation, Yi Zhou
    Abstract: Imitation learning from human demonstrations has shown impressive performance in robotics. However, most results focus on table-top manipulation, lacking the mobility and dexterity necessary for generally useful tasks. In this work, we develop a system for imitating mobile manipulation tasks that are bimanual and require whole-body control. We first present Mobile ALOHA, a low-cost and whole-body teleoperation system for data collection. It augments the ALOHA system with a mobile base, and a whole-body teleoperation interface. Using data collected with Mobile ALOHA, we then perform supervised behavior cloning and find that co-training with existing static ALOHA datasets boosts performance on mobile manipulation tasks. With 50 demonstrations for each task, co-training can increase success rates by up to 90%, allowing Mobile ALOHA to autonomously complete complex mobile manipulation tasks such as sauteing and serving a piece of shrimp, opening a two-door wall cabinet to store heavy cooking pots, calling and entering an elevator, and lightly rinsing a used pan using a kitchen faucet. We will open-source all the hardware and software implementations upon publication.

History

2024

2023

2022

2021

2020

  • [Topic] [ The path planning algorithm for multiple mobile edge servers in EdgeGO], Rong Cong, 2020-11-18

2019

2018

2017

Instructions

请使用Latest_seminar和Hist_seminar模板更新本页信息.

    • 修改时间和地点信息
    • 将当前latest seminar部分的code复制到这个页面中
    • 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=
    • 填入latest seminar各字段信息
    • 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
  • 格式说明
    • Latest_seminar:

{{Latest_seminar
|confname=
|link=
|title=
|speaker=
}}

    • Hist_seminar

{{Hist_seminar
|confname=
|link=
|title=
|speaker=
|date=
}}

Retrieved from "http://mobinets.cn/site/index.php?title=Resource:Seminar&oldid=3465"