InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning

• URL: http://arxiv.org/abs/2505.23867v3
• Date: Wed, 08 Oct 2025 09:46:14 GMT
• Title: InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning
• Authors: Zeyu Liu, Zhitian Hou, Guanghao Zhu, Zhijie Sang, Congkai Xie, Hongxia Yang,
• Abstract summary: We introduce our InfiMed-Series models, InfiMed-SFT-3B and InfiMed-RL-3B, both of which deliver state-of-the-art performance across seven multimodal medical benchmarks.<n>InfiMed-RL-3B achieves an average accuracy of 59.2%, outperforming even larger models like InternVL3-8B, which achieves 57.3%.
• Score: 19.791150694039466
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in domains such as visual understanding and mathematical reasoning. However, their application in the medical domain is constrained by two key challenges: (1) multimodal medical datasets are scarce and often contain sparse information, limiting reasoning depth; and (2) Reinforcement Learning with Verifiable Rewards (RLVR), though effective in general domains, cannot reliably improve model performance in the medical domain. To overcome these challenges, during the supervised fine-tuning (SFT) stage, we incorporate high-quality textual reasoning data and general multimodal data alongside multimodal medical data to efficiently enhance foundational medical capabilities and restore the base model's reasoning ability. Moreover, considering that there are some multimodal medical datasets with sparse information, we further synthesize reflective-pattern-injected chain-of-thought (CoT) in addition to general CoT samples, equipping the model with initial reflective reasoning capabilities that provide a structured foundation for subsequent RLVR training. Finally, we introduce our InfiMed-Series models, InfiMed-SFT-3B and InfiMed-RL-3B, both of which deliver state-of-the-art performance across seven multimodal medical benchmarks. Notably, InfiMed-RL-3B achieves an average accuracy of 59.2%, outperforming even larger models like InternVL3-8B, which achieves 57.3%. Specifically, during the SFT phase, we utilized 188K samples, while the RLVR phase incorporated 36K samples, demonstrating the efficacy of both training strategies in achieving superior performance. We also conducted a series of extensive experiments, which provide valuable insights that contribute to advancing the performance of MLLMs in medical scenarios.

Related papers

• MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images [25.29568841502814]
  We introduce MedMO, a medical foundation model built upon a generalized MLLM architecture.<n>On VQA benchmarks, MedMO achieves an average accuracy improvement of +13.7% over the baseline.<n>In medical report generation, MedMO delivers significant gains in both semantic and clinical accuracy.
  arXiv  Detail & Related papers  (2026-02-06T18:59:59Z)
• Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs [7.542510160217106]
  We propose Fleming-VL, a framework for comprehensive medical visual understanding across heterogeneous modalities.<n>Fleming-VL achieves state-of-the-art performance across multiple benchmarks, including medical VQA, video QA, and 3D medical image understanding.
  arXiv  Detail & Related papers  (2025-11-02T12:30:22Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation [55.37355146924576]
  MedSeqFT is a sequential fine-tuning framework for medical image analysis.<n>It adapts pre-trained models to new tasks while refining their representational capacity.<n>It consistently outperforms state-of-the-art fine-tuning strategies.
  arXiv  Detail & Related papers  (2025-09-07T15:22:53Z)
• MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration [57.98393950821579]
  We introduce the Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis (MAM)<n>Inspired by our empirical findings, MAM decomposes the medical diagnostic process into specialized roles: a General Practitioner, Specialist Team, Radiologist, Medical Assistant, and Director.<n>This modular and collaborative framework enables efficient knowledge updates and leverages existing medical LLMs and knowledge bases.
  arXiv  Detail & Related papers  (2025-06-24T17:52:43Z)
• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning [57.873833577058]
  We build a multimodal dataset enriched with extensive medical knowledge.<n>We then introduce our medical-specialized MLLM: Lingshu.<n>Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities.
  arXiv  Detail & Related papers  (2025-06-08T08:47:30Z)
• Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation [0.0]
  This research paper investigates the application of Large Language Models (LLMs) in healthcare.<n>We focus on enhancing medical decision support through Retrieval-Augmented Generation (RAG) integrated with hospital-specific data and fine-tuning using Quantized Low-Rank Adaptation (QLoRA)<n>We touch on the ethical considerations-patient privacy, data security, and the need for rigorous clinical validation-as well as the practical challenges of integrating such systems into real-world healthcare.
  arXiv  Detail & Related papers  (2025-05-06T10:31:54Z)
• Med-CoDE: Medical Critique based Disagreement Evaluation Framework [72.42301910238861]
  The reliability and accuracy of large language models (LLMs) in medical contexts remain critical concerns.<n>Current evaluation methods often lack robustness and fail to provide a comprehensive assessment of LLM performance.<n>We propose Med-CoDE, a specifically designed evaluation framework for medical LLMs to address these challenges.
  arXiv  Detail & Related papers  (2025-04-21T16:51:11Z)
• Performance of Large Language Models in Supporting Medical Diagnosis and Treatment [0.0]
  AI-driven systems can analyze vast datasets, assisting clinicians in identifying diseases, recommending treatments, and predicting patient outcomes.<n>This study evaluates the performance of a range of contemporary LLMs, including both open-source and closed-source models, on the 2024 Portuguese National Exam for medical specialty access.
  arXiv  Detail & Related papers  (2025-04-14T16:53:59Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions.<n>We propose a novel approach utilizing structured medical reasoning.<n>Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models [18.6994780408699]
  Large Language Models (LLMs) face significant challenges in medical question answering.<n>We propose a novel approach incorporating similar case generation within a multi-agent medical question-answering system.<n>Our method capitalizes on the model's inherent medical knowledge and reasoning capabilities, eliminating the need for additional training data.
  arXiv  Detail & Related papers  (2024-12-31T19:55:45Z)
• Demystifying Large Language Models for Medicine: A Primer [50.83806796466396]
  Large language models (LLMs) represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare. This tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice.
  arXiv  Detail & Related papers  (2024-10-24T15:41:56Z)
• SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction Generation [13.672776832197918]
  Multimodal large language models (MLLMs) have made significant strides, yet they face challenges in the medical domain due to limited specialized knowledge. We seek to address this gap at various stages of the end-to-end learning pipeline, including data collection, model fine-tuning, and evaluation.
  arXiv  Detail & Related papers  (2024-10-19T02:35:35Z)
• FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models [54.09244105445476]
  This study introduces a novel knowledge injection approach, FedKIM, to scale the medical foundation model within a federated learning framework.<n>FedKIM leverages lightweight local models to extract healthcare knowledge from private data and integrates this knowledge into a centralized foundation model.<n>Our experiments across twelve tasks in seven modalities demonstrate the effectiveness of FedKIM in various settings.
  arXiv  Detail & Related papers  (2024-08-17T15:42:29Z)
• HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale [29.956053068653734]
  We create the PubMedVision dataset with 1.3 million medical VQA samples. Using PubMedVision, we train a 34B medical MLLM HuatuoGPT-Vision, which shows superior performance in medical multimodal scenarios.
  arXiv  Detail & Related papers  (2024-06-27T15:50:41Z)
• 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)
• RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning [14.366349078707263]
  RJUA-MedDQA is a comprehensive benchmark in the field of medical specialization. This work introduces RJUA-MedDQA, a comprehensive benchmark in the field of medical specialization.
  arXiv  Detail & Related papers  (2024-02-19T06:57:02Z)
• A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models [57.88111980149541]
  We introduce Asclepius, a novel Med-MLLM benchmark that assesses Med-MLLMs in terms of distinct medical specialties and different diagnostic capacities.<n>Grounded in 3 proposed core principles, Asclepius ensures a comprehensive evaluation by encompassing 15 medical specialties.<n>We also provide an in-depth analysis of 6 Med-MLLMs and compare them with 3 human specialists.
  arXiv  Detail & Related papers  (2024-02-17T08:04:23Z)
• Federated Learning Enables Big Data for Rare Cancer Boundary Detection [98.5549882883963]
  We present findings from the largest Federated ML study to-date, involving data from 71 healthcare institutions across 6 continents. We generate an automatic tumor boundary detector for the rare disease of glioblastoma. We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent.
  arXiv  Detail & Related papers  (2022-04-22T17:27:00Z)

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.