AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published 17 days ago • 101
HumanNet: Scaling Human-centric Video Learning to One Million Hours Paper • 2605.06747 • Published 23 days ago • 52
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 53