BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20250519T110000
DTEND;TZID=Asia/Hong_Kong:20250519T120000
DTSTAMP:20260509T211548
CREATED:20250603T024808Z
LAST-MODIFIED:20250603T025046Z
UID:111483-1747652400-1747656000@ece.hku.hk
SUMMARY:Symmetric Diffusers: Learning Discrete Diffusion on Finite Symmetric Groups
DESCRIPTION:We regret to inform you that the event has been cancelled and will be postponed to a later date.  \nAbstract\nFinite symmetric groups Sn are essential in fields such as combinatorics\, physics\, and chemistry. However\, learning a probability distribution over Sn poses significant challenges due to its intractable size and discrete nature. We introduce SymmetricDiffusers\, a novel discrete diffusion model that simplifies the task of learning a complicated distribution over Sn by decomposing it into learning simpler transitions of the reverse diffusion using deep neural networks. We identify the riffle shuffle as an effective forward transition and provide empirical guidelines for selecting the diffusion length based on the theory of random walks on finite groups. Additionally\, we propose a generalized Plackett-Luce (PL) distribution for the reverse transition\, which is provably more expressive than the PL distribution. We further introduce a theoretically grounded “denoising schedule” to improve sampling and learning efficiency. Extensive experiments show that our model achieves state-of-the-art or comparable performances on solving tasks including sorting 4-digit MNIST images\, jigsaw puzzles\, and traveling salesman problems. \nSpeaker\nProf. Renjie LIAO\nDepartment of Electrical and Computer Engineering\, and\nDepartment of Computer Science\,\nUniversity of British Columbia (UBC) \nSpeaker’s Biography\nRenjie Liao is an Assistant Professor in the Department of Electrical and Computer Engineering and an Associate Member of the Department of Computer Science at the University of British Columbia (UBC). He is also a faculty member at the Vector Institute and holds a Canada CIFAR AI Chair. Prior to joining UBC\, he was a Visiting Faculty Researcher at Google Brain\, working with Geoffrey Hinton and David Fleet. He received his Ph.D. in Computer Science from the University of Toronto in 2021\, under the supervision of Richard Zemel and Raquel Urtasun. During his Ph.D.\, he also worked as a Senior Research Scientist at Uber Advanced Technologies Group. He holds an M.Phil. in Computer Science from the Chinese University of Hong Kong (2015) and a B.Eng. in Automation from Beihang University (2011). His research interests span machine learning and its intersection with computer vision\, self-driving\, healthcare\, and beyond\, with a particular focus on probabilistic and geometric deep learning. \nOrganiser\nProf. Xiaojuan QI\nDepartment of Electrical and Electronic Engineering\,\nThe University of Hong Kong \nAll are welcome!
URL:https://ece.hku.hk/events/20250519-1/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Highlights,Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20250519T153000
DTEND;TZID=Asia/Hong_Kong:20250519T163000
DTSTAMP:20260509T211548
CREATED:20250603T034323Z
LAST-MODIFIED:20250603T034323Z
UID:111564-1747668600-1747672200@ece.hku.hk
SUMMARY:Distributed Mixture-of-Expert Systems at the Wireless Edge
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/93486553339 \nAbstract\nThe emergence of distributed Mixture-of-Experts (DMoE) systems\, which deploy expert models at edge nodes\, offers a pathway to achieving connected intelligence in sixth-generation (6G) mobile networks and edge artificial intelligence (AI). However\, current DMoE systems lack an effective expert selection algorithm to address the simultaneous task-expert relevance and channel diversity inherent in these systems. Traditional AI or communication systems focus on either performance or channel conditions\, and direct application of these methods leads to high communication overhead or low performance. To address this\, we propose the DMoE protocol to schedule the expert inference and inter-expert transmission. This protocol identifies expert selection and subcarrier allocation as key optimization problems. We formulate an expert selection problem by incorporating both AI performance and channel conditions\, and further extend it to a Joint Expert and Subcarrier Allocation (JESA) problem for comprehensive AI and channel management within the DMoE framework. For the NP-hard expert selection problem\, we introduce the Dynamic Expert Selection (DES) algorithm\, which leverages a linear relaxation as a bounding criterion to significantly reduce search complexity. For the JESA problem\, we discover a unique structural property that ensures asymptotic optimality in most scenarios. We propose an iterative algorithm that addresses subcarrier allocation as a subproblem and integrates it with the DES algorithm. The proposed framework effectively manages the tradeoff between task relevance and channel conditions through a tunable importance factor\, enabling flexible adaptation to diverse scenarios. Numerical experiments validate the dual benefits of the proposed expert selection algorithm: high performance and significantly reduced cost. JESA consistently achieves higher accuracy compared to homogeneous expert selection and lowers the cost by up to 50% compared to Top-k scheduling. \nSpeaker\nMr. Shengling Qin\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nSpeaker’s Biography\nShengling Qin received the B.Eng. degree from Tsinghua University\, China\, in 2023. He is currently working towards MPhil degree with The University of Hong Kong\, Hong Kong. His research interests include mixture-of-experts\, large language models and distributed training. \n\n\n\nAll are welcome!
URL:https://ece.hku.hk/events/20250519-2/
LOCATION:Online via Zoom
CATEGORIES:Highlights,Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20250519T160000
DTEND;TZID=Asia/Hong_Kong:20250519T170000
DTSTAMP:20260509T211548
CREATED:20250603T024619Z
LAST-MODIFIED:20250603T041708Z
UID:111476-1747670400-1747674000@ece.hku.hk
SUMMARY:Strategies on Perovskite Nanocrystals for Achieving High-Performance Light Emitting Devices
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/92719085356?pwd=09aQ3vjvg9bhXcObBYxjNtj4UVx5V4.1 \n\nAbstract\nMixed-chloride/bromide perovskite nanocrystals (PeNCs) are known for their advantages in pure blue emission\, but often suffer from halogen segregation. This study investigates the ligand exchange process with different ion pair combinations to improve stability. Surprisingly\, altering the ligand ion combinations leads to a deviation from pure blue emission in CsPbBrxCl3-x nanocrystals due to halogen redistribution influenced by solubility principles in a non-polar environment. Furthermore\, a novel approach is demonstrated in this study by capping p-type cuprous sulfide (Cu2S) over Cs3Cu2I5 to enhance hole mobility in Cu-based perovskite nanocrystals. The resulting Cs3Cu2I5/Cu2S nanocrystals exhibit improved hole mobility and photoluminescence quantum yield\, leading to enhanced electroluminescent performance in white perovskite light-emitting diodes (W-PeLEDs). \nSpeaker\nMr. LI Dongyu\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nSpeaker’s Biography\nLI Dongyu received the M.S. degree from Jilin University in 2019. He is currently pursuing his Ph.D. degree with the Department of Electrical and Electronic Engineering\, The University of Hong Kong. His research interest is semiconductor materials and their application in light-emitting devices. \nAll are welcome!
URL:https://ece.hku.hk/events/20250519-01/
LOCATION:Online via Zoom
CATEGORIES:Highlights,Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
END:VCALENDAR