{
  "id": 16226,
  "url": "https://arxiv.org/abs/2608.03316",
  "title": "Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging",
  "summary": "On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher latents cannot serve as targets in a foreign coordinate",
  "authors": "Siming Fu, Zheming Fu, Ruizhe He, Hualiang Wang, Jie Huang, Xiaoxiao Ma",
  "category": "research",
  "topics": "regulation,children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-03T20:00:00.000Z",
  "fetched_at": "2026-08-05T05:10:44.550Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/16226",
  "original_url": "https://arxiv.org/abs/2608.03316",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}