Speaker: Dr. Yilun Xu, MIT & NVIDIA

Time: 16:00 p.m., Jun 13, 2024, GMT+8

Venue: Room 204, Courtyard No.5, Jingyuan

Abstract: 

Physics-inspired generative models such as diffusion models constitute a powerful family of generative models. The advantages of models in this family come from relatively stable training process and high capacity. A number of possible improvements remain possible. In this talk, I will discuss the enhancement and design of physics-inspired generative models. I will first present a sampling algorithm that combines the best of previous samplers, greatly accelerating the generation speed of text-to-image Stable Diffusion models. Additionally, I will discuss sampling methods to promote diversity in finite samples, by adding mutual repulsion forces between samples in the generative process. Secondly, I will discuss a training framework that introduces learnable discrete latents into continuous diffusion models. These latents simplify complex noise-to-data mappings and reduce the curvature of generative trajectories. Finally, I will introduce Poisson Flow Generative Models (PFGM), a new generative model arising from electrostatic theory, rivaling leading diffusion models. The extended version, PFGM++, places diffusion models and PFGM under the same framework and introduces new, better models. Several algorithms discussed in the talk are the state-of-the-art methods across standard benchmarks.

Source: Center on Frontiers of Computing Studies, PKU