MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation

Documenti analoghi

• MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
  di: Yan, Zhonghao, et al.
  Pubblicazione: (2025)
• Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
  di: Ma, Wen, et al.
  Pubblicazione: (2026)
• MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
  di: Xu, Huihui, et al.
  Pubblicazione: (2025)
• MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data
  di: Zhang, Mengmeng, et al.
  Pubblicazione: (2026)
• Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation
  di: Shen, Jiachen, et al.
  Pubblicazione: (2023)