# MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models

Source: [MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models](<https://www.sota2.com/research/paper/68fa7be01e209131cea8af8e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:50:18.755Z

Authors: Soo Yong Kim, Suin Cho, Vincent-Daniel Yun, Gyeongyeon Hwang

Published: 2025-10-06T04:26:39.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.04477>)

[PDF](<https://arxiv.org/pdf/2510.04477.pdf>)
