SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation Paper • 2511.19320 • Published 7 days ago • 39
Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment Paper • 2511.22345 • Published 4 days ago • 7
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training Paper • 2203.12602 • Published Mar 23, 2022 • 1
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models Paper • 2504.15271 • Published Apr 21 • 67
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions Paper • 2511.03334 • Published 26 days ago • 51