arXiv q-bio + cs.AI: clinical/medical
From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation
추론에서 픽셀로: VQA와 분할을 위한 기반 의료 멀티모달 LLM
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.