Computer Vision Lunch Series: Dr. Liwei Wang, "Learning from Videos for 3D Spatial Understanding and Interaction."
- Event Type
- Seminar/Symposium
- Sponsor
- Siebel School of Computing and Data Science
- Location
- 2405 Siebel Center
- Date
- Dec 12, 2025 12:30 pm
- Speaker
- Dr. Liwei Wang
- Contact
- Allison Mette
- agk@illinois.edu
- Originating Calendar
- Siebel School Speakers Calendar
What to Expect: In this talk, Liwei will discuss recent advances in Multimodal Large Language Models (MLLMs) and the persistent challenges they face in spatial understanding and reasoning within complex 3D environments. Despite strong progress, current models—largely trained on 2D data—still struggle to capture the nuances of 3D scenes, even with added 3D information. Lwiei will present new approaches that enable efficient and robust 3D perception and reasoning directly from video.
Bio: Dr. Liwei Wang is an Assistant Professor in the Department of Computer Science and Engineering at The Chinese University of Hong Kong (CUHK). Prior to joining CUHK, he was a Senior Researcher at Tencent America in Bellevue, WA. He got his Ph.D. in Computer Science from the University of Illinois Urbana-Champaign (UIUC), where he was advised by Prof. Svetlana Lazebnik. At CUHK, Dr. Wang leads the Language and Vision (LaVi) Lab, which conducts research at the intersection of natural language processing and computer vision. His work focuses on enabling machines to understand and interact with the visual world in a multi-modal way. His research interests include language modeling, multi-modal models, video-language understanding, learning spatial intelligence from videos, large model evaluation, etc. Dr. Wang has also served as an Area Chair for AI conferences, such as CVPR, ECCV, ICML, ACL, and NeurIPS.