PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Paper • 2603.25730 • Published 11 days ago • 50
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published 13 days ago • 91
FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow Paper • 2603.19598 • Published 17 days ago • 32
