DyMD: Preserving Interaction Dynamics through Distribution Matching Distillation in Few-Step Video World Models
Large video diffusion models offer expressive priors for embodied prediction and learning, yet their many-step sampling remains costly for interactive downstream use. Distribution Matching Distillation (DMD) enables few-step video generation, but can suppress robot--object motion while preserving visual quality. Examining DMD's teacher and fake-score signals, we find that weak re-noising keeps…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.