48 min
Compositional Reasoning with Diffusion Models
Artificial Intelligence, Machine Learning and seminar by Yilun Du, Harvard University
Friday 09:45 Los Angeles (GMT-7)
Recording available
Berkeley, United States
Recording
Abstract
Diffusion and energy-based models can support reasoning by searching during inference and combining separate learned components. This talk develops that compositional perspective and examines how smaller models can jointly solve more complex questions. Empirical examples cover symbolic reasoning, decisions and planning.