WorldRover Collection Paired 360 + first-person video of photoreal scenes, with per-frame depth, camera pose and actions. • 5 items • Updated 5 days ago
Marionette: Predicting World States, Rendering Geometry, Painting Appearance Paper • 2608.14530 • Published 10 days ago • 33
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World Paper • 2608.13546 • Published 11 days ago • 132
HelloWorld: Enabling Socially Interactive Characters in Video World Models Paper • 2608.05070 • Published 19 days ago • 40
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow Paper • 2607.28362 • Published 25 days ago • 22