MedVLThinker: Simple Baselines for Multimodal Medical Reasoning

• URL: http://arxiv.org/abs/2508.02669v1
• Date: Mon, 04 Aug 2025 17:59:38 GMT
• Title: MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
• Authors: Xiaoke Huang, Juncheng Wu, Hui Liu, Xianfeng Tang, Yuyin Zhou,
• Abstract summary: We present MedVLThinker, a suite of simple yet strong baselines for building reasoning-centric medical LMMs.<n>Our fully open recipe consists of: (1) systematic data curation for both text-only and image-text medical data, filtered according to varying levels of reasoning difficulty, and (2) two training paradigms:Supervised Fine-Tuning (SFT) on distilled reasoning traces and Reinforcement Learning with Verifiable Rewards (RLVR) based on final answer correctness.
• Score: 21.849783391186754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models (LRMs) have introduced a new paradigm in AI by enabling models to ``think before responding" via chain-of-thought reasoning. However, the absence of open and reproducible recipes for building reasoning-centric medical LMMs hinders community-wide research, analysis, and comparison. In this paper, we present MedVLThinker, a suite of simple yet strong baselines. Our fully open recipe consists of: (1) systematic data curation for both text-only and image-text medical data, filtered according to varying levels of reasoning difficulty, and (2) two training paradigms: Supervised Fine-Tuning (SFT) on distilled reasoning traces and Reinforcement Learning with Verifiable Rewards (RLVR) based on final answer correctness. Across extensive experiments on the Qwen2.5-VL model family (3B, 7B) and six medical QA benchmarks, we find that RLVR consistently and significantly outperforms SFT. Additionally, under the RLVR framework, a key, counter-intuitive finding is that training on our curated text-only reasoning data provides a more substantial performance boost than training on multimodal image-text data. Our best open 7B model, trained using the RLVR recipe on text-only data, establishes a new state-of-the-art on existing public VQA benchmarks, surpassing all previous open-source medical LMMs. Furthermore, scaling our model to 32B achieves performance on par with the proprietary GPT-4o. We release all curated data, models, and code to provide the community with a strong, open foundation for future research in multimodal medical reasoning.

Related papers

• MIRA: A Novel Framework for Fusing Modalities in Medical RAG [6.044279952668295]
  We introduce the Multimodal Intelligent Retrieval and Augmentation (MIRA) framework, designed to optimize factual accuracy in MLLM.<n>MIRA consists of two key components: (1) a calibrated Rethinking and Rearrangement module that dynamically adjusts the number of retrieved contexts to manage factual risk, and (2) A medical RAG framework integrating image embeddings and a medical knowledge base with a query-rewrite module for efficient multimodal reasoning.
  arXiv  Detail & Related papers  (2025-07-10T16:33:50Z)
• Efficient Medical VIE via Reinforcement Learning [10.713109515157475]
  Visual Information Extraction (VIE) converts unstructured document images into structured formats like, structured formats like, critical for medical applications like report analysis and online consultations.<n>Traditional methods rely on OCR and language models, while end-to-end multimodal models offer direct generation.<n>We base our approach on the Reinforcement Learning with Verifiable Rewards (RLVR) framework to address these challenges using only 100 annotated samples.
  arXiv  Detail & Related papers  (2025-06-16T11:10:25Z)
• Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning [71.3533541927459]
  We propose a novel data selection paradigm termed Activation Reasoning Potential (RAP)<n>RAP identifies cognitive samples by estimating each sample's potential to stimulate genuine multi-modal reasoning.<n>Our RAP method consistently achieves superior performance using only 9.3% of the training data, while reducing computational costs by over 43%.
  arXiv  Detail & Related papers  (2025-06-05T08:40:24Z)
• Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL [26.138061467729212]
  We present AlphaMed, the first medical LLM to show that reasoning capability can emerge purely through reinforcement learning (RL)<n>AlphaMed achieves state-of-the-art results on six medical QA benchmarks, outperforming models trained with conventional SFT+RL pipelines.<n>Our findings show that dataset informativeness is a key driver of reasoning performance, and that minimalist RL on informative, multiple-choice QA data is effective at inducing reasoning without CoT supervision.
  arXiv  Detail & Related papers  (2025-05-23T14:27:37Z)
• GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning [28.911445780180077]
  This paper presents GMAI-VL-R1, a multimodal medical reasoning model enhanced by reinforcement learning (RL) to improve its reasoning abilities.<n>We develop a reasoning data synthesis method, generating step-by-step reasoning data via rejection sampling, which further enhances the model's generalization.<n> Experimental results show that after RL training, GMAI-VL-R1 excels in tasks such as medical image diagnosis and visual question answering.
  arXiv  Detail & Related papers  (2025-04-02T16:43:16Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles [91.88062410741833]
  We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning.<n>We show that OpenVLThinker-7B consistently advances performance across six benchmarks demanding mathematical and general reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning [19.064630697040055]
  Reinforcement learning from verifiable rewards (RLVR) has recently gained attention for its ability to elicit self-evolved reasoning from base language models without explicit reasoning supervisions.<n>We introduce Med-RLVR as an initial study of RLVR in the medical domain leveraging medical multiple-choice question answering (MCQA) data as verifiable labels.<n>Our results demonstrate that RLVR is not only effective for math and coding but also extends successfully to medical question answering.
  arXiv  Detail & Related papers  (2025-02-27T00:54:38Z)
• Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluation [113.5002649181103]
  Training open-source small multimodal models (SMMs) to bridge competency gaps for unmet clinical needs in radiology. For training, we assemble a large dataset of over 697 thousand radiology image-text pairs. For evaluation, we propose CheXprompt, a GPT-4-based metric for factuality evaluation, and demonstrate its parity with expert evaluation. The inference of LlaVA-Rad is fast and can be performed on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
  arXiv  Detail & Related papers  (2024-03-12T18:12:02Z)
• Aligning Large Multimodal Models with Factually Augmented RLHF [176.54751941088819]
  Large Multimodal Models (LMM) are built across modalities and misalignment between two modalities can result in "hallucination" We adapt the Reinforcement Learning from Human Feedback (RLHF) from the text domain to the task of vision-language alignment. We propose a new alignment algorithm called Factually Augmented RLHF that augments the reward model with additional factual information. Our approach achieves remarkable improvement on the LLaVA-Bench dataset with the 94% performance level of the text-only GPT-4.
  arXiv  Detail & Related papers  (2023-09-25T20:59:33Z)
• Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study [60.56194508762205]
  We reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. We present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models.
  arXiv  Detail & Related papers  (2023-04-21T11:54:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.