MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation
MedVol-R1:基于奖励驱动的证据基础用于体积推理分割
机构 * School of Biological Science and Medical Engineering, Beihang University, Beijing, China(生物科学与医学工程学院,北京航空航天大学) ; Center for Information and Computer Science, School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University, Kanagawa, Japan(信息与计算机科学中心,开放与环境系统科学学院,科技研究生学校,东京大学,神奈川,日本) ; Bytedance Inc., China(字节跳动公司,中国) ; Tsinghua University, Beijing, China(清华大学,北京,中国)
专题命中 视觉定位与Grounding :grounding(title,abstract);分类 cs.CV、cs.AI
AI总结 提出MedVol-R1框架,通过强化学习将临床推理解耦为可验证的2D证据锚点,再传播为3D掩膜,实现体积推理分割,在多个基准上达到最优性能。