BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.16.0//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:20250101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20260515T140000
DTEND;TZID=Asia/Hong_Kong:20260515T150000
DTSTAMP:20260513T064900
CREATED:20260512T081414Z
LAST-MODIFIED:20260512T081414Z
UID:115938-1778853600-1778857200@ece.hku.hk
SUMMARY:RPG Seminar – Stabilizing Streaming Video Geometry via Dynamic Feature Normalization
DESCRIPTION:Zoom Link \nhttps://hku.zoom.us/j/94833409754?pwd=ER6VaveQbdEzOQzhuFKThpSdRusUDs.1 \nAbstract\nConsistent 3D geometry estimation from streaming RGB input is crucial for real-world applications such as autonomous driving\, embodied AI\, and large-scale reconstruction. \nWhile modern monocular geometry foundation models achieve strong single-image accuracy\, they exhibit severe temporal inconsistency on continuous input\, notably dominated by scale–shift drifting. Through targeted empirical analysis\, we trace this instability to its root cause: fluctuations in latent feature statistics\, whose mean and variance directly determine the predicted depth’s scale and shift. Building on this insight\, we introduce Dynamic Feature Normalization (DyFN)\, a lightweight\, causal recurrent module that dynamically and robustly modulates feature statistics to maintain stable geometry over time. We adapt powerful pretrained monocular geometry models for streaming by finetuning only DyFN\, a mere 2% additional parameters\, while keeping the backbone frozen\, thereby achieving temporal consistency without compromising single-image accuracy. Extensive experiments across four benchmarks show that DyFN effectively eliminates temporal artifacts such as disjointed layering and positional jitter\, and achieves state-of-the-art temporal stability\, improving over prior streaming methods by up to 14% and even outperforming heavier non-causal video baselines. \nSpeaker\nMr Xiaoyang LYU\nDepartment of Electrical and Computer Engineering\nThe University of Hong Kong \nBiography of the Speaker\nXiaoyang Lyu is a fourth-year PhD student in the CVMI Lab at the University of Hong Kong\, where he is supervised by Prof. Xiaojuan Qi. He holds a Master’s degree from Zhejiang University and a Bachelor’s degree from the Harbin Institute of Technology.\nXiaoyang’s research focuses on bridging the gap between physical and digital environments by replicating complex physics\, geometry\, and material properties within simulators. He is driven by the conviction that high-fidelity world modeling is essential for advancing embodied AI and developing agents that can effectively assist in the real world. \nOrganiser\nProf Xiaojuan QI \nDepartment of Electrical and Computer Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20260515-2/
CATEGORIES: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:20260515T160000
DTEND;TZID=Asia/Hong_Kong:20260515T170000
DTSTAMP:20260513T064900
CREATED:20260511T020048Z
LAST-MODIFIED:20260511T020048Z
UID:115888-1778860800-1778864400@ece.hku.hk
SUMMARY:RPG Seminar – Unveiling the Relationship Between Cation Content and Zeta Potential of Colloids for Forming High-Quality Perovskites
DESCRIPTION:Zoom Link \nhttps://hku.zoom.us/j/94017530661 \nAbstract\nThere are numerous studies focusing on the crystallization dynamics of perovskite materials. However\, the change of precursor properties which can also significantly affect crystallization behavior\, is always ignored. In this seminar\, we establish a comprehensive understanding of the relationship between A-site cations content and zeta potential of precursor\, revealing its influence on perovskite formation and crystallization dynamics. Through in-situ photoluminescence (PL) and X-ray diffraction (XRD) analyses\, we demonstrate how zeta potential impacts the formation process and crystallization behavior of perovskites. Furthermore\, we explore the effects of zeta potential on the optical and electrical properties of the resulting materials. Our findings indicate that achieving a zeta potential near zero facilitates the fabrication of high-quality and additive-free perovskites\, leading to enhanced performance in perovskite solar cells (PSCs) and perovskite light-emitting diodes (PeLEDs). This work provides vital insights into tuning interfacial properties for improved perovskite optoelectronic devices. \nSpeaker\nMr. Qi XIONG\nDepartment of Electrical and Computer Engineering\nThe University of Hong Kong \nBiography of the Speaker\nQi Xiong received the B.S. degree in Polymer Materials and Engineering from Hainan University\, and the M.S. degree in Material Science and Engineering from South China University of Technology. He is currently pursuing the Ph.D. degree in the Department of Electrical and Computer Engineering\, Faculty of Engineering\, The University of Hong Kong. His current research interests include perovskite synthesis and blue perovskite light-emitting diodes (PeLEDs). \nOrganiser\nProf. Wallace C.H. CHOY \nDepartment of Electrical and Computer Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20260515/
CATEGORIES: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:20260519T160000
DTEND;TZID=Asia/Hong_Kong:20260519T170000
DTSTAMP:20260513T064900
CREATED:20260420T064633Z
LAST-MODIFIED:20260420T064633Z
UID:115720-1779206400-1779210000@ece.hku.hk
SUMMARY:RPG Seminar – From Understanding to Intervention: Interpretability-Guided Methods for Improving Large Language Models
DESCRIPTION:  \nAbstract\nLarge language models have achieved impressive performance\, but improving them efficiently and reliably requires more than scaling alone. In this talk\, I present a series of works that explore how internal understanding of LLMs can be translated into practical interventions for better capability\, efficiency\, and controllability. I begin with actionable mechanistic interpretability\, introducing a unified “Locate\, Steer\, and Improve” perspective that turns model analysis into a framework for intervention. I then show how this perspective supports several concrete advances: data-free mixed-precision quantization guided by numerical and structural sensitivity\, multilingual capability enhancement through representation shifting and contrastive alignment\, personalized multi-teacher distillation that routes each prompt to its most suitable teacher\, and coarse-to-fine selective fine-tuning for mitigating catastrophic forgetting while preserving general versatility. Together\, these works reflect a common theme: interpretability is not only a tool for explaining LLMs\, but also a principled basis for designing more efficient training\, compression\, and adaptation methods. \nSpeaker\nMr Hengyuan ZHANG\nDepartment of Electrical and Computer Engineering\nThe University of Hong Kong \nBiography of the Speaker\nHengyuan Zhang is a Ph.D. candidate at the University of Hong Kong\, supervised by Prof. Ngai Wong and Prof. Hayden Kwok-Hay So. His research focuses on the improvement of efficiency and interpretability within large language models. He aims to uncover and characterize the internal processes that govern model behavior\, with the goal of improving model speciality\, interpretability\, and reliability in real-world deployments. He has published multiple papers in leading venues such as ACL\, EMNLP\, TKDD\, and NeurIPS. \nOrganiser\nProf. Ngai WONG \nDepartment of Electrical and Computer Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20260519/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
END:VCALENDAR