About this paper
Endpoint Distribution Matching Distillation trains a shared fake model only on final student outputs and adds precise teacher supervision to better align few-step diffusion students with teacher distributions for 4-step generation.
Distribution matching distillation (DMD) has emerged as a leading paradigm for distilling diffusion models into few-step students, where an auxiliary fake score model tracks the student's distribution and the discrepancy between the teacher and fake predictions drives the student toward the teacher. In multi-step distillation, although only the student's final output is delivered, existing methods train the fake model on intermediate states or across all denoising steps. Consequently, the student's update signal becomes entangled with intermediate distributions, which can distort the matching direction and remain nonzero even after the student's final outputs already match the teacher…
distribution matching distillationdiffusion modelsfew-step studentsfake score modelteacher predictionsmulti-step distillationdenoising stepsintermediate distributionsEndpoint Distribution Matching DistillationeDMD
- Upvotes
- 14
- Authors
- 7
- Published
- Nov 12, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
eDMD: Endpoint Distribution Matching for Few-Step Diffusion Distillation was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 7 checks on 1 different day. Its best position was #12 of 30, reached on Nov 17, 17:28 UTC. It dropped off the list after Nov 17, 19:28 UTC.