2 papers
cs.CV2026
Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT
Zhenyu Bu, Haoyan Ding, Chushu Shen +7
Accurate 3D abnormality segmentation in chest CT requires dense spatial supervision, but obtaining expert voxel-level labels is costly. Radiology reports, however, are routinely ge…
cs.CV2026
V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning
Shulin Tian, Minglun Li, Yuhao Dong +6
Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or intermediate inference can u…