Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds Paper • 2611.08286 • Published 8 days ago • 2
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction Paper • 2606.18558 • Published Jun 17 • 54
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory Paper • 2505.23617 • Published May 29, 2025