VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding Paper • 2606.05259 • Published 17 days ago • 39
MIDAS: Multimodal Interactive Digital-human Synthesis via Real-time Autoregressive Video Generation Paper • 2508.19320 • Published Aug 26, 2025 • 29
KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution Paper • 2505.00497 • Published May 1, 2025 • 17