Harold Haodong Chen

PhysOPSD uses executable simulation code as privileged context for on-policy self-distillation in video generation: the student sees only text, while the teacher additionally sees a physics draft rendered from the simulation, so the model learns physically plausible motion without changing its inference interface. On the UniVideo (13B) and OmniWeaving (8.3B) backbones it trains on 3K samples and scores higher on VideoPhy-2 overall and PhyGround than supervised fine-tuning with 80K samples and offline reinforcement learning with 21K samples, while VBench general quality is maintained or slightly improved.

PhysOPSD uses executable simulation code as privileged context for on-policy self-distillation in video generation: the student sees only text, while the teacher additionally sees a physics draft rendered from the simulation, so the model learns physically plausible motion without changing its inference interface. On the UniVideo (13B) and OmniWeaving (8.3B) backbones it trains on 3K samples and scores higher on VideoPhy-2 overall and PhyGround than supervised fine-tuning with 80K samples and offline reinforcement learning with 21K samples, while VBench general quality is maintained or slightly improved.