Abstract:

Data-driven AI models scale impressively, yet they still struggle with rigorous modeling of the physical world. In this talk, we present hybrid machine learning models that bridge AI with physical modeling through two complementary principles. The first is tool interaction: rather than embedding physical knowledge directly into data-driven models, we enable machine learning systems to actively interact with external physical modeling tools. The second is physics-enriched data scaling: instead of merely increasing the size of training datasets, we enrich data with physically informative feedback derived from modeling and simulation. We demonstrate that these principles are broadly compatible with both symbolic and vision systems, and show their impact across diverse domains, including scientific reasoning, theorem proving, and simulations of complex 4D environments.

Bio:

Dr. Wuyang Chen is a tenure-track Assistant Professor in Computing Science at Simon Fraser University. Previously, he was a postdoctoral researcher in Statistics at the University of California, Berkeley, advised by Professor Michael Mahoney. He obtained his Ph.D. in Electrical and Computer Engineering from the University of Texas at Austin in 2023, advised by Professor Atlas Wang. Dr. Chen’s research focuses on integrating AI methods with physical knowledge, scientific machine learning, and theoretical understanding of deep networks. Dr. Chen has published papers at CVPR, ECCV, ICLR, ICML, NeurIPS, and other top conferences. Dr. Chen’s research has been recognized by the US NSF newsletter, two Doctoral Dissertation Awards from INNS and iSchools, AAAI New Faculty Highlights, and Nvidia Academic Grant Award. Dr. Chen is the host of the Foundation Models for Science workshop at NeurIPS 2024 and co-organized the 4th and 5th versions of the UG2+ workshop and challenge at CVPR in 2021 and 2022.
 

Zoom Link