The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding Paper • 2512.19693 • Published 3 days ago • 60
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models Paper • 2501.08453 • Published Jan 14 • 1
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models Paper • 2503.18886 • Published Mar 24 • 24
RepVideo: Rethinking Cross-Layer Representation for Video Generation Paper • 2501.08994 • Published Jan 15 • 15