AI RESEARCH
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
arXiv CS.CV
•
ArXi:2605.06376v1 Announce Type: new Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce self-consistency along the full PF-ODE trajectory to steer it toward the clean data manifold, vanilla DMD relies on sparse supervision at a few predefined discrete timesteps.