CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation Paper • 2601.11096 • Published Jan 16 • 8
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models Paper • 2601.11087 • Published Jan 16 • 11
Mimir: Improving Video Diffusion Models for Precise Text Understanding Paper • 2412.03085 • Published Dec 4, 2024 • 12