LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory Paper • 2603.03269 • Published 21 days ago • 61
view article Article Introducing Waypoint-1: Real-time interactive video diffusion from Overworld +3 Jan 20 • 40
DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer Paper • 2601.01425 • Published Jan 4 • 53
End-to-End Training for Autoregressive Video Diffusion via Self-Resampling Paper • 2512.15702 • Published Dec 17, 2025 • 16