AI RESEARCH
Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation
arXiv CS.LG
•
ArXi:2606.02237v1 Announce Type: new Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales. In principle, such distribution-level supervision remains agnostic to specific noise-data pairings of the teacher; this provides the student the freedom to remap latent noise, a behavior consistently observed in low-dimensional settings.