DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation

ArXi:2603.25931v1 Announce Type: cross Flow-matching video generators produce temporally coherent, high-fidelity outputs yet routinely violate elementary physics because their reconstruction objectives penalize per-frame deviations without distinguishing physically consistent dynamics from impossible ones. Contrastive flow matching offers a principled remedy by pushing apart velocity-field trajectories of differing conditions, but we identify a fundamental obstacle in the text-conditioned video setting: semantic-physics entanglement.