{"ID":2859688,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04477","arxiv_id":"2510.04477","title":"MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models","abstract":"Bridging clinical diagnostic reasoning with AI remains a central challenge in medical imaging. We introduce MedCLM, an automated pipeline that converts detection datasets into large-scale medical visual question answering (VQA) data with Chain-of-Thought (CoT) reasoning by linking lesion boxes to organ segmentation and structured rationales. These contextual signals enable medical vision-language models to generate question-answer pairs with step-by-step reasoning. To utilize this data effectively, we propose an Integrated CoT-Curriculum Strategy composed of an Easy stage with explicit lesion boxes for visual grounding, a Medium stage that encourages implicit localization, and a Hard stage for weakly supervised reasoning. Experimental results demonstrate that MedCLM attains state-of-the-art performance on several medical VQA benchmarks, providing a scalable framework for developing clinically aligned medical vision-language models.","short_abstract":"Bridging clinical diagnostic reasoning with AI remains a central challenge in medical imaging. We introduce MedCLM, an automated pipeline that converts detection datasets into large-scale medical visual question answering (VQA) data with Chain-of-Thought (CoT) reasoning by linking lesion boxes to organ segmentation and...","url_abs":"https://arxiv.org/abs/2510.04477","url_pdf":"https://arxiv.org/pdf/2510.04477v1","authors":"[\"Soo Yong Kim\",\"Suin Cho\",\"Vincent-Daniel Yun\",\"Gyeongyeon Hwang\"]","published":"2025-10-06T04:26:39Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}