arXiv Machine Learning By Shucheng Li, Iolo Jones, Alexander Tong, Michael M. Bronstein

Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation

Read the original on arXiv Machine Learning →

arXiv:2606. 02237v1 Announce Type: new Abstract: Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI
3d ago

GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across Scales

The paper introduces GFD-OPD, a method for on‑policy distillation of diffusion models that addresses challenges when compressing large teachers into smaller students. It identifies that standard distillation fails due to distribution gaps and classifier‑free guidance amplification, and proposes Fixed‑State KL to measure these gaps. GFD‑OPD reduces the student‑teacher discrepancy and achieves state‑of‑the‑art performance across multiple benchmarks.

By Zhenxing Zhang, Jiayan Teng, Wenxu Wu, Zhuoyi Yang, Jiazheng Xu, Wendi Zheng, Jie Tang, Dan Guo, Meng Wang
arXiv Machine Learning
Jun 5

OPRD: On-Policy Representation Distillation

arXiv:2606. 06021v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities.

By Shenzhi Yang, Guangcheng Zhu, Bowen Song, Haobo Wang, Mingxuan Xia, Xing Zheng, Yingfan Ma, Zhongqi Chen, Weiqiang Wang, Gang Chen