Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
(5 intermediate revisions by 2 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2025-03-07 10:30-12:00'''
|time='''2025-04-11 10:30-12:00'''
|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 = 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.
|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.
|confname = Arxiv
|confname = Mobisys'24
|link = https://arxiv.org/abs/2502.02508
|link = https://dl.acm.org/doi/abs/10.1145/3643832.3661888
|title= Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
|title= CACTUS: Dynamically Switchable Context-aware micro-Classifiers for Efficient IoT Inference
|speaker=Qinyong
|speaker= Zhenhua
|date=2025-03-14
|date=2025-04-18
}}{{Latest_seminar
}}
|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.
{{Latest_seminar
|confname =ToN'23
|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.
|link = https://ieeexplore.ieee.org/document/10371205/
|confname = TC'24
|title= LiFi for Low-Power and Long-Range RF Backscatter
|link = https://ieeexplore.ieee.org/document/10360355
|speaker=Mengyu
|title= A GPU-Enabled Real-Time Framework for Compressing and Rendering Volumetric Videos
|date=2025-03-14
|speaker=Mengfan
|date=2025-04-18
}}
}}


{{Resource:Previous_Seminars}}
{{Resource:Previous_Seminars}}

Revision as of 10:54, 18 April 2025

Time: 2025-04-11 10:30-12:00
Address: 4th Research Building A518
Useful links: 📚 Readling list; 📆 Schedules; 🧐 Previous seminars.

Latest

  1. [Mobisys'24] CACTUS: Dynamically Switchable Context-aware micro-Classifiers for Efficient IoT Inference, Zhenhua
    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.
  2. [TC'24] A GPU-Enabled Real-Time Framework for Compressing and Rendering Volumetric Videos, Mengfan
    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.

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
    • 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=
}}