AI RESEARCH
Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals
arXiv CS.CV
•
ArXi:2510.27684v2 Announce Type: replace Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of one-step distilled models compromises generative diversity and degrades performance in complex generative tasks, e.g., generating intricate object motions in text-to-video task.