Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think Paper • 2410.06940 • Published Oct 9, 2024 • 11
Efficient Long Video Tokenization via Coordinated-based Patch Reconstruction Paper • 2411.14762 • Published Nov 22, 2024 • 11
Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition Paper • 2403.14148 • Published Mar 21, 2024 • 21