Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration Paper • 2605.17423 • Published 23 days ago • 33
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published 27 days ago • 101
Olaf-World: Orienting Latent Actions for Video World Modeling Paper • 2602.10104 • Published Feb 10 • 27
Code2World: A GUI World Model via Renderable Code Generation Paper • 2602.09856 • Published Feb 10 • 201
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands Paper • 2512.24965 • Published Dec 31, 2025 • 43
DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection Paper • 2511.19111 • Published Nov 24, 2025 • 3