{
  "id": 15879,
  "url": "https://arxiv.org/abs/2608.02252v1",
  "title": "HarMoE: Multi-Source Chest Radiograph Pretraining with Dataset-Disentangled Experts",
  "summary": "Recent vision-language models for chest X-ray understanding are largely built on image-report alignment and therefore rely heavily on MIMIC-CXR as the dominant pretraining source. While effective at scale, this paradigm underexplores an important alternative source of supervision: a range of existing multi-label classification datasets, which provide cleaner and more explicit disease signals than free-text reports, and can offer broader pathology coverage when combined across sources. However, l",
  "authors": "Haozhe Luo, Ziyu Zhou, Shelley Zixin Shu, Mauricio Reyes",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-03T14:00:16.000Z",
  "fetched_at": "2026-08-04T05:10:21.797Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/15879",
  "original_url": "https://arxiv.org/abs/2608.02252v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}