{
  "id": 17087,
  "url": "https://arxiv.org/abs/2608.05683v1",
  "title": "DistMedVL: Distributional Vision-Language Alignment for Uncertainty-Aware Medical Image Segmentation",
  "summary": "Cross-modal alignment of visual and textual representations is fundamental to multimodal medical image understanding, yet remains hindered by uncertainty in both modalities under real-world clinical conditions. Existing vision-language segmentation methods rely on deterministic cross-modal matching, which overlooks aleatoric uncertainty from ambiguous boundaries and epistemic uncertainty from limited training data, leading to fragile performance under domain shift. To address this issue, we prop",
  "authors": "Jiaxuan Li, Qing Xu, Xiangjian He, Yue Li, Daokun Zhang, Fiseha B. Tesema et al.",
  "category": "research",
  "topics": "safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T07:17:14.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/17087",
  "original_url": "https://arxiv.org/abs/2608.05683v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}