{
  "id": 18759,
  "url": "https://arxiv.org/abs/2608.11205",
  "title": "AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss",
  "summary": "Fréchet distance has recently emerged as an effective distribution-level objective for generator post-training, complementing the conventional sample-level diffusion and flow-matching losses. However, directly optimizing Fréchet objectives can cause Fréchet hacking. The target metrics keep improving, but visual quality and Fréchet alignment in other feature spaces may stagnate or deteriorate. We attribute this failure to the static pretrained feature spaces used by existing Fréchet losses. These",
  "authors": "Mingju Gao, Jingkai Zhou, Kun Gai, Changqian Yu, Hao Tang",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T20:00:00.000Z",
  "fetched_at": "2026-08-13T05:10:37.786Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/18759",
  "original_url": "https://arxiv.org/abs/2608.11205",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}