{
  "id": 14027,
  "url": "https://arxiv.org/abs/2607.24731v1",
  "title": "Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation",
  "summary": "On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is under-identified at the branch level: positive- and negat",
  "authors": "Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu, Jinpeng Yu, Yang Shi, Jiaming Liu, Ruihua Huang",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-27T17:57:02.000Z",
  "fetched_at": "2026-07-28T05:10:12.325Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14027",
  "original_url": "https://arxiv.org/abs/2607.24731v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}