{
  "id": 6679,
  "url": "https://arxiv.org/abs/2603.26049v1",
  "title": "Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays",
  "summary": "Despite recent advances in medical vision-language pretraining, existing models still struggle to capture the diagnostic workflow: radiographs are typically treated as context-agnostic images, while radiologists' gaze -- a crucial cue for visual reasoning -- remains largely underexplored by existing methods. These limitations hinder the modeling of disease-specific patterns and weaken cross-modal alignment. To bridge this gap, we introduce CoGaze, a Context- and Gaze-guided vision-language pretr",
  "authors": "Kang Liu, Zhuoqi Ma, Siyu Liang, Yunan Li, Xiyue Gao, Chao Liang et al.",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-27T03:37:52.000Z",
  "fetched_at": "2026-07-14T16:32:41.665Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6679",
  "original_url": "https://arxiv.org/abs/2603.26049v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}