The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
arXiv:2606.05328v2 Announce Type: replace-cross Abstract: Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this question by probing video diffusion models along latent trajectories corresponding to real videos with known physical plausibility. To obtain…