{
  "id": 18015,
  "url": "https://arxiv.org/abs/2608.09287v1",
  "title": "UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillation",
  "summary": "Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating the need for access to the original training dataset. Existing DFKD methods rely heavily on architecture-specific statistical priors (e.g., Batch Normalization statistics) to guide data synthesis, however, such architecture-dependent priors are often absent in modern architectures such as Vision Transformers (ViTs), resu",
  "authors": "Xuewan He, Tong Chu, Zihan Cheng, Yuchen Su, Qianxin Xia, Guoming Lu et al.",
  "category": "research",
  "topics": "children-education",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T08:39:55.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18015",
  "original_url": "https://arxiv.org/abs/2608.09287v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}