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-WR-CALNAME:Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
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:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20241218T103000
DTEND;TZID=Asia/Hong_Kong:20241218T113000
DTSTAMP:20260510T213036
CREATED:20241210T012223Z
LAST-MODIFIED:20250211T042315Z
UID:107413-1734517800-1734521400@ece.hku.hk
SUMMARY:Unlocking the Value of Single Modality through Multi-Modal Knowledge Transfer for Healthcare
DESCRIPTION:Abstract\nRecent years have witnessed the remarkable success of deep neural networks in healthcare\, particularly in the analysis of medical images and signals. However\, their performance is often constrained by the scarcity of labelled data\, driven by high labelling costs and challenges related to data privacy and sharing. In this talk\, I will explore how we can overcome these limitations by leveraging multi-modal data through advanced learning frameworks to enhance the capabilities of single modality analysis. Specifically\, I will present our recent and ongoing work\, including those accepted at MICCAI 2023 and MICCAI 2024. This talk will delve into the details of innovative techniques such as large language model-informed pretraining and multi-modal learning for X-ray images and ECG signals\, as well as demonstrating how these approaches can significantly contribute to more accurate\, reliable\, and cost-effective healthcare solutions. \nSpeaker\nProf. Chen (Cherise) Chen\nLecturer (Assistant Professor) in Computer Vision\,\nSchool of Computer Science\,\nUniversity of Sheffield\, UK \nBiography of the Speaker\nChen (Cherise) Chen is currently a Lecturer (assistant professor) in Computer Vision at the School of Computer Science\, University of Sheffield\, UK. Previously\, she was a postdoc at Imperial College London (ICL) and then the University of Oxford. She obtained her MSc and Ph.D. from the Department of Computing at Imperial College London in 2016 and 2022\, respectively\, where she worked closely with Prof. Daniel Rueckert and Dr. Wenjia Bai. Chen also has accumulated valuable industrial experience. She worked as a research scientist at Infervision Inc. in Beijing in 2017\, prior to her PhD\, and later as a part-time research scientist at HeartFlow\, UK\, in 2022 following her PhD. Her research focuses on the intersection of AI and healthcare\, particularly in developing data-efficient\, robust\, and explainable AI for clinical applications. So far\, she has published more than 40 papers in leading conferences and high-impact journals on deep learning for medical data analysis such as MICCAI\, ECCV\, IEEE TMI\, and Medical Image Analysis\, accumulating over 2\,000 Google Scholar citations and an h-index of 20. She is a program chair for MIDL 2025; session and area chair for MICCAI 2024 and serves as lead organisers in several MICCAI workshops and challenges including\, MICCAI ADSMI 2024\, DALI 2023\, and the CMRxMotion Challenge. Very recently\, she has also been appointed as an ELLIS Scholar at the European Laboratory for Learning and Intelligent Systems in 2024. https://cherise215.github.io. \nOrganiser\nProf. Cheng Chen\nDepartment of Electrical and Electronic Engineering\,\nThe University of Hong Kong \nAll are welcome!
URL:https://ece.hku.hk/events/20241218-2/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Highlights,Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/12/1280-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20241218T150000
DTEND;TZID=Asia/Hong_Kong:20241218T160000
DTSTAMP:20260510T213036
CREATED:20241128T022442Z
LAST-MODIFIED:20250211T042315Z
UID:19513-1734534000-1734537600@ece.hku.hk
SUMMARY:Toward Scalable Generative AI via Mixture of Experts in Mobile Edge Networks
DESCRIPTION:Abstract\nThe evolution of generative artificial intelligence (GAI) has driven revolutionary applications like ChatGPT. The proliferation of these applications is underpinned by the mixture of experts (MoE)\, which contains multiple experts and selectively engages them for each task to lower operation costs while maintaining performance. Despite MoE’s efficiencies\, GAI still faces challenges in resource utilization when deployed on local user devices. Therefore\, we first propose mobile edge networks supported MoE-based GAI. Rigorously\, we review the MoE from traditional AI and GAI perspectives\, scrutinizing its structure\, principles\, and applications. Next\, we present a new framework for using MoE for GAI services in Metaverse. Moreover\, we propose a framework that transfers subtasks to devices in mobile edge networks\, aiding GAI model operation on user devices. Moreover\, we introduce a novel approach utilizing MoE\, augmented with Large Language Models (LLMs)\, to analyze user objectives and constraints of optimization problems based on deep reinforcement learning (DRL) effectively. This approach selects specialized DRL experts\, and weights each decision from the participating experts. In this process\, the LLM acts as the gate network to oversee the expert models\, facilitating a collective of experts to tackle a wide range of new tasks. Furthermore\, it can also leverage LLM’s advanced reasoning capabilities to manage the output of experts for joint decisions. Lastly\, we insightfully identify research opportunities of MoE and mobile edge networks. \nSpeaker\nProf. Dusit Niyato\nPresident’s Chair Professor\,\nCollege of Computing & Data Science (CCDS)\,\nNanyang Technological University\, Singapore \nBiography of the Speaker\nDusit Niyato is a President’s Chair Professor in the College of Computing & Data Science (CCDS)\, Nanyang Technological University\, Singapore. Dusit’s research interests are in the areas of mobile generative AI\, edge intelligence\, quantum computing and networking\, and incentive mechanism design. Dusit won the IEEE Vehicular Technology Society Stuart Meyer Memorial Award. Dusit won the IEEE Vehicular Technology Society Stuart Meyer Memorial Award. Currently\, Dusit is serving as Editor-in-Chief of IEEE Communications Surveys and Tutorials (impact factor of 34.4 for 2023) and will serve as the Editor-in-Chief of IEEE Transactions on Network Science and Engineering (TNSE) from 2025. He is also an area editor of IEEE Transactions on Vehicular Technology (TVT)\, topical editor of IEEE Internet of Things Journal (IoTJ)\, lead series editor of IEEE Communications Magazine\, and associate editor of IEEE Transactions on Wireless Communications (TWC)\, IEEE Transactions on Mobile Computing (TMC)\, IEEE Wireless Communications\, IEEE Network\, IEEE Transactions on Information Forensics and Security (TIFS)\, IEEE Transactions on Cognitive Communications and Networking (TCCN)\, IEEE Transactions on Services Computing (TSC)\, and ACM Computing Surveys. Dusit is the Members-at-Large to the Board of Governors of IEEE Communications Society for 2024-2026. He was named the 2017-2023 highly cited researcher in computer science. He is a Fellow of IEEE and a Fellow of IET. \nOrganiser\nProf. Hongyang Du\nDepartment of Electrical and Electronic Engineering\,\nThe University of Hong Kong \nAll are welcome!
URL:https://ece.hku.hk/events/20241218-1/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Highlights,Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/1280.jpg
END:VEVENT
END:VCALENDAR