AI RESEARCH

ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models

arXiv CS.CV

ArXi:2605.08567v1 Announce Type: new Action-conditioned world models (ACWMs) have shown strong promise for video prediction and decision-making. However, existing benchmarks are largely restricted to egocentric navigation or narrow, task-specific robotics datasets, offering only limited coverage of the rich physical interactions required for generalized world understanding. We