Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
m
 
(151 intermediate revisions by 5 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2023-06-01 9:30'''
|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=In the last decade, LoRa has emerged and prevailed as a promising technology to offer the long range and low power communication service. The packet collisions caused by concurrent transmissions(CTs) severely limit the LoRa network capacity, which becomes the key obstacle to releasing the potential of LoRa. The existing collision-resolution researches need frequency domain features to separate different packets in the collision. When there exists multiple packets in the collision, these features are more likely to overlap with each other and cannot be distinguished, which leads to performance degradation of these studies. To address this issue, in this paper, we propose channel hopping LoRa (CHLoRa) as a physical approach that utilize the multi-channel diversity to against multi-packet collisions. In CHLoRa, the LoRa chirp is divided into several subchirps and spread into different channels. As all the subchirp-pieces of the original chirp are likely to be collided with the subchirps with different bins, CHLoRa can recover the original chirp’s bin through merging the same bins of its subchirps. However, it is hard to obtain precise demodulation results of subchirps especially in collision, as using shorter time-span subchirps decreases the frequency resolution. We propose a subchirp merging scheme to group and merge subchirps’ bins according to their collision-free confidence. We conduct simulation experiments to evaluate the performance of CHLoRa. The results show that ...
|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=INFOCOM 2024
|confname =EMNLP'25
|link=https://mobinets.org/index.php?title=Resource:Seminar
|link = https://arxiv.org/abs/2501.18460
|title=CHLoRa: Pushing the Limits of LoRa Concurrent Transmissions with Channel Hopping Subchirps
|title= ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
|speaker=Wenliang}}
|speaker=Youwei Ran
|date=2025-12-12
}}
{{Latest_seminar
{{Latest_seminar
|abstract = Accurate, real-time object detection on resource-constrained devices enables autonomous mobile vision applications such as traffic surveillance. However, analyzing real-time video poses severe challenges to today’s network and computation systems. Rather than either pure local processing or offloading, we merge large objects across the boundary locally and objects from the edge. To balance accuracy, latency, payment and reliability, we present EdgeLight, a crowd-assisted real-time video analytics framework, which coordinates computationally weak cameras with more powerful edge servers to enable video analytics under the accuracy, latency and payment requirements of applications. Furthermore, we design a connectionless service discovery protocol to reduce invalid wifi connections.
|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=SEC 2023
|confname =CoRL'24
|link=https://mobinets.org/index.php?title=Resource:Seminar
|link = https://openreview.net/forum?id=FO6tePGRZj
|title=EdgeLight: Smart Traffic Lights with Ambient Edge Intelligence
|title= Mobile ALOHA: Learning Bimanual Mobile Manipulation using Low-Cost Whole-Body Teleoperation
|speaker=Xianyang}}
|speaker=Yi Zhou
 
|date=2025-12-12
 
}}
 
=== 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"