Abstract:

Robust simulation and precise modeling of physical dynamics are essential for advancing perception, planning, and control in the development of generalist physical agents. In this talk, I will present my research on building generative models that combine physical realism with scalability in high-dimensional environments. The presentation delves into both the theoretical foundations and practical implementations of our methods, including the incorporation of 3D constraints into video diffusion models and the integration of autoregressive structures into continuous generative modeling to better handle complex data. By combining these techniques, the models replicate intricate interactions in dynamic scenes and demonstrate their potential to support efficient, data-driven learning across a broad range of applications.

Zoom Link: https://upenn.zoom.us/j/92594955973