Research

A review of Oasis: A Universe in a transformer, and Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

A review of papers that add controllabilities to video generation (DragNUWA and Boximator)

Elucidating the Design Space of Diffusion-Based Generative Models, focusing on the rationale behind its engineering details.

DDPM and score-based SDEs as two routes to reverse diffusion, contrasting their shared structure and modeling differences.