Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
 
(122 intermediate revisions by 4 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''Thursday 9:00-10:30'''
|time='''2025-12-12 10:30'''
|addr=4th Research Building A518
|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
{{Latest_seminar
|abstract=While a number of recent efforts have explored the use of "cloud offload" to enable deep learning on IoT devices, these have not assumed the use of duty-cycled radios like BLE. We argue that radio duty-cycling significantly diminishes the performance of existing cloud-offload methods. We tackle this problem by leveraging a previously unexplored opportunity to use early-exit offload enhanced with prioritized communication, dynamic pooling, and dynamic fusion of features. We show that our system, FLEET, achieves significant benefits in accuracy, latency, and compute budget compared to state-of-art local early exit, remote processing, and model partitioning schemes across a range of DNN models, datasets, and IoT platforms.
|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=MobiCom '23
|confname =EMNLP'25
|link=https://dl.acm.org/doi/10.1145/3570361.3592514
|link = https://arxiv.org/abs/2501.18460
|title=Re-thinking computation offload for efficient inference on IoT devices with duty-cycled radios
|title= ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
|speaker=Yang Wang
|speaker=Youwei Ran
|date=2024-01-11}}
|date=2025-12-12
}}
{{Latest_seminar
{{Latest_seminar
|abstract=Provenance tracking has been widely used in the recent literature to debug system vulnerabilities and find the root causes behind faults, errors, or crashes over a running system. However, the existing approaches primarily developed graph-based models for provenance tracking over monolithic applications running directly over the operating system kernel. In contrast, the modern DevOps-based service-oriented architecture relies on distributed platforms, like serverless computing that uses container-based sandboxing over the kernel. Provenance tracking over such a distributed micro-service architecture is challenging, as the application and system logs are generated asynchronously and follow heterogeneous nomenclature and logging formats. This paper develops a novel approach to combining system and micro-services logs together to generate a Universal Provenance Graph (UPG) that can be used for provenance tracking over serverless architecture. We develop a Loadable Kernel Module (LKM) for runtime unit identification over the logs by intercepting the system calls with the help from the control flow graphs over the static application binaries. Finally, we design a regular expression-based log optimization method for reverse query parsing over the generated UPG. A thorough evaluation of the proposed UPG model with different benchmarked serverless applications shows the system’s effectiveness.
|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=INFOCOM '23
|confname =CoRL'24
|link=https://ieeexplore.ieee.org/abstract/document/10228884
|link = https://openreview.net/forum?id=FO6tePGRZj
|title=DisProTrack: Distributed Provenance Tracking over Serverless Applications
|title= Mobile ALOHA: Learning Bimanual Mobile Manipulation using Low-Cost Whole-Body Teleoperation
|speaker=Xinyu
|speaker=Yi Zhou
|date=2024-01-11}}
|date=2025-12-12
{{Latest_seminar
}}
|abstract=While radio communication still dominates in 5G, light and radios are expected to complement each other in the coming 6G networks. Visible Light Communication (VLC) is therefore attracting a tremendous amount of attention from both academia and industry. Recent studies showed that the front camera of pervasive smartphones is an ideal candidate to serve as the VLC receiver. While promising, we observe a recent trend with smartphones that can greatly hinder the adoption of smartphones for VLC, i.e., smartphones are moving towards full-screen for the best user experience. This trend forces front cameras to be placed under the devices' screen---leading to the so-called Under-Screen Camera (USC)---but we observe a severe performance degradation in VLC with USC: the transmission range is reduced from a few meters to merely 0.04 m, and the throughput is decreased by more than 90%. To address this issue, we leverage the unique spatiotemporal characteristics of the rolling shutter effect on USC to design a pixel-sweeping algorithm to identify the sampling points with minimal interference from the translucent screen. We further propose a novel slope-boosting demodulation method to deal with color shift brought by the leakage interference. We build a proof-of-concept prototype using two commercial smart-phones. Experiment results show that our proposed design reduces the BER by two orders of magnitude on average and improves the data rate by 59×: from 914 b/s to 54.43 kb/s. The transmission range is extended by roughly 100×: from 0.04 m to 4.2 m.
|confname=MobiSys '23
|link=https://dl.acm.org/doi/abs/10.1145/3581791.3596855
|title=When VLC Meets Under-Screen Camera
|speaker=Jiacheng
|date=2024-01-11}}
{{Latest_seminar
|abstract=While recent work explored streaming volumetric content on-demand, there is little effort on live volumetric video streaming that bears the potential of bringing more exciting applications than its on-demand counterpart. To fill this critical gap, in this paper, we propose MetaStream, which is, to the best of our knowledge, the first practical live volumetric content capture, creation, delivery, and rendering system for immersive applications such as virtual, augmented, and mixed reality. To address the key challenge of the stringent latency requirement for processing and streaming a huge amount of 3D data, MetaStream integrates several innovations into a holistic system, including dynamic camera calibration, edge-assisted object segmentation, cross-camera redundant point removal, and foveated volumetric content rendering. We implement a prototype of MetaStream using commodity devices and extensively evaluate its performance. Our results demonstrate that MetaStream achieves low-latency live volumetric video streaming at close to 30 frames per second on WiFi networks. Compared to state-of-the-art systems, MetaStream reduces end-to-end latency by up to 31.7% while improving visual quality by up to 12.5%.
|confname=MobiCom '23
|link=https://dl.acm.org/doi/abs/10.1145/3570361.3592530
|title=MetaStream: Live Volumetric Content Capture, Creation, Delivery, and Rendering in Real Time
|speaker=Jiale
|date=2024-01-11}}
{{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"