Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
 
(22 intermediate revisions by 2 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2025-10-24 10:30'''
|time='''2026-04-10 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]].
Line 8: Line 8:


{{Latest_seminar
{{Latest_seminar
|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.
|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.
|confname = Sensys'24
|confname =OSDI'25
|link = https://dl.acm.org/doi/10.1145/3666025.3699344
|link = https://www.usenix.org/conference/osdi25/presentation/cheng
|title= MagicStream: Bandwidth-conserving Immersive Telepresence via Semantic Communication
|title= PipeThreader: Software-defined pipelining for efficient DNN execution
|speaker= Mengfan Wang
|speaker=Junzhe
|date=2025-10-31
|date=2026-4-9
}}{{Latest_seminar
|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.
|confname = Systems Joural
|link = https://ieeexplore.ieee.org/document/11024019
|title= Collaborative Task Offloading for LEO Satellite Internet of Things: A Novel Computing Coordinate Graph-Based Approach
|speaker= Yifei Zhou
|date=2025-10-31
}}
}}
{{Resource:Previous_Seminars}}
{{Resource:Previous_Seminars}}

Latest revision as of 10:37, 10 April 2026

Time: 2026-04-10 10:30
Address: 4th Research Building A518
Useful links: 📚 Readling list; 📆 Schedules; 🧐 Previous seminars.

Latest

  1. [OSDI'25] PipeThreader: Software-defined pipelining for efficient DNN execution, Junzhe
    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.

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=3511"