PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Paper • 2603.25730 • Published 9 days ago • 48
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published 11 days ago • 90
WorldAgents: Can Foundation Image Models be Agents for 3D World Models? Paper • 2603.19708 • Published 15 days ago • 12
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding Paper • 2603.19235 • Published 16 days ago • 94
