AI RESEARCH
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
arXiv CS.LG
•
ArXi:2605.30116v1 Announce Type: cross Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously evolving generator, making