{
  "id": 18256,
  "url": "https://arxiv.org/abs/2608.09818v1",
  "title": "MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation",
  "summary": "Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack precise localization, whereas medical segmenters typically rely on explicit target categories or precise spatial prompts. This divide is reinforced by a supervision mismatch: segmentation datasets provide precise masks but little language supervision, whereas medical vision-language data rarely pair language with dense sp",
  "authors": "Haoyu Yang, Meixing Shi, Zengjie Chen, Haoran Sun, Haitao Leng, Xiaoming Shi, Yuxiang Cai, Yankai Jiang",
  "category": "research",
  "topics": "healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T16:37:24.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/18256",
  "original_url": "https://arxiv.org/abs/2608.09818v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}