الباحثون

Junkun Yuan

المنشورات 2

نسخة أولية وصول مفتوح

DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation

Zhengming Yu, Junkun Yuan, Haotian Yang وآخرون · 2026

Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving distribution at extra memory and computation cost. We introduce DMAD, Distribution Matching as Adve …

نسخة أولية وصول مفتوح

PDMD: Projected Distribution Matching Distillation for Video Diffusion Models

Zimo Wang, Junkun Yuan, Angtian Wang وآخرون · 2026

Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. However, DMD samples can degrade during training, exhibiting progressive oversaturation and artifacts. We …

المؤلفون المشاركون