BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.16.3//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:20260602T103000
DTEND;TZID=Asia/Hong_Kong:20260602T113000
DTSTAMP:20260602T060628
CREATED:20260529T100852Z
LAST-MODIFIED:20260601T084435Z
UID:117024-1780396200-1780399800@ece.hku.hk
SUMMARY:Seminar on Physics-Aware World Model for Video Generation and Embodied AI
DESCRIPTION:The seminar on “Physics-Aware World Model for Video Generation and Embodied AI” is rescheduled to begin at 10:30 am. \nAbstract\nIn AI and cognitive science\, world models are key for planning\, reasoning\, and learning from experience. An effective world model needs to: sense and learn real-world knowledge\, predict and generate real-world scenes\, reason and control according to physical laws\, and act robustly with human-in-the-loop. Prior work on world models has limited capability in representation/generation and physical awareness. We overcome these limitations through two innovations\, and towards the first open-source\, physically grounded world model from academia. First\, we develop a flow matching and DPO reinforcement learning framework to improve the continuity and physical awareness in world model representation and generation. Our world model PhyWorld achieves simultaneously best-of-the-results in physical awareness and state-of-the-art in open-source video generation. Second\, we develop a comprehensive physical awareness benchmarking and arena system. We extract comprehensively 50-60 metrics demonstrating physical law awareness of video generation and trajectory. Our comprehensive benchmark PhyGround includes video quality\, common sense\, Newtonian mechanics\, optics\, energy\, chemical\, materials\, etc.\, which is missing in literature. We generate an agent and a 9B language model for evaluating physical awareness according to these benchmarks. Last\, we describe our effort and results towards the concept of “world model for all”\, which utilises a single world model for robotic control and robot navigation\, task management\, planning\, task decomposition for high-level management and control\, as well as automatic SLAM and 3D reconstruction for environment sensing. \nSpeaker\nProf. Yanzhi WANG\nProfessor\,\nDepartment of Electrical and Computer Engineering\,\nNortheastern University \nSpeaker’s Biography\nYanzhi WANG is a Professor in the Department of Electrical and Computer Engineering and Computer Science at Northeastern University\, a senior member of IEEE. His research interests focus on real-time and energy-efficient deep learning and artificial intelligence systems\, especially on efficient large language models and large-scale generative AI systems. His research works have been published broadly in (i) machine learning conferences such as AAAI\, CVPR\, NeurIPS\, ICML\, ICCV\, ICLR\, IJCAI\, ECCV\, KDD\, ICRA\, ACM MM\, ICDM\, etc.\, (ii) architecture and system conferences such as ASPLOS\, ISCA\, MICRO\, HPCA\, CCS\, VLDB\, PLDI\, WWW\, ICS\, PACT\, CGO\, IPDPS\, INFOCOM\, ICDCS\, DAC\, ICCAD\, FPGA\, FCCM\, ISSCC\, CICC\, RTAS\, RTSS\, etc.\, and (iii) IEEE and ACM transactions. His research works have been cited 29\,000 times. He has received six Best Paper Awards and another 12 Best Paper Nominations. He has many research awards\, including the U.S. Army Young Investigator Award and other young investigator awards\, research awards from Google\, Intel\, Mathworks\, etc. His research work has been reported and cited by around 500 media. He has 18 academic descendants as tenure-track faculty members at the University of Minnesota\, University of Massachusetts Amherst\, University of Arizona\, City University of Hong Kong\, University of Georgia\, Zhejiang University\, etc. His alumni have become key contributors in Google Gemini and Alibaba Qwen 3. \nOrganiser\nProf. Kaibin HUANG\nDepartment of Electrical and Computer Engineering\,\nThe University of Hong Kong\n\nAll are welcome!
URL:https://ece.hku.hk/events/20260602-1/
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/2026/05/1280-1.jpg
END:VEVENT
END:VCALENDAR