BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Human-centric Spatial Intelligence: World Models for Egoce
 ntric 3D Agents - Lu Chen\, Zhejiang University
DTSTART:20251016T100000Z
DTEND:20251016T110000Z
UID:TALK238972@talks.cam.ac.uk
CONTACT:Elliott Wu
DESCRIPTION:Intelligence arises not only from seeing the world\, but also 
 from interacting with it. Through this continuous observation and interact
 ion\, humans develop internal world models that predict how their actions 
 shape the environment\, and rely on these models to guide everyday decisio
 ns. This talk explores how such models can be learned and utilized by egoc
 entric 3D agents—AI systems that perceive from a first-person view\, act
  through 3D body motions\, and plan by simulating the consequences of thei
 r actions. Using EgoAgent (ICCV 2025) as an example\, I will show how visu
 al representation learning\, motion prediction\, and world modeling can be
  unified within a clean and mutually reinforcing framework. I will conclud
 e by discussing future steps toward richer spatial understanding and more 
 reliable autonomous agents.\n\n\nBio: Lu Chen is a Ph.D. student at the St
 ate Key Laboratory of CAD&CG\, Zhejiang University\, advised by Prof. Xiao
 wei Zhou. His research interests lie in computer vision and visualization\
 , with a focus on world models and human-centric learning. He received his
  B.Eng. degree from Shandong University\, where he was awarded the Taishan
  Honors College Dean’s Award for Excellence.
LOCATION:https://cam-ac-uk.zoom.us/j/89933570670?pwd=UEUqBVK9raqRf0vlnvseN
 rUKAxGGRx.1
END:VEVENT
END:VCALENDAR