GRASP: Group-Adaptive Hybrid RL-SFT Post-Training for Medical VQA without Reasoning Annotations.

arXiv:2610.34561v1 Announce Type: cross Abstract: Adapting general-purpose vision-language models (VLMs) to medical visual question answering (VQA) is valuable for helping clinicians read images and make diagnoses, but annotated data are scarce and provide onl