Open-source alternatives to CLIP DR

Multimodal large language models (MLLMs) have made significant strides, yet they face challenges in the medical domain due to limited specialized knowledge. While recent medical MLLMs demonstrate strong performance in lab settings, they often struggle in real-world applications, highlighting a…

MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

Kun Yuan, Vinkle Srivastav, Tong Yu, Joel L. Lavanchy, Pietro Mascagni, Nassir Navab, Nicolas Padoy

Official code for the Paper "RaDialog: A Large Vision-Language Model for Radiology Report Generation and Conversational Assistance"

The official code for "Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data".

M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization), MICCAI 2023.

NEWS!This paper has been accpeted by MICCAI 2023 Sorry that I had the autumn recruitment in China a few months ago, and I did not update the open source trend of the paper. I have found a satisfactory job and returned to scientific research yet!! Remaining code is being updated per week !!

torch >= 1.11.0

🤖 Model | 🤗 Dataset | 📖 Paper

EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model

【ICML 2025 Spotlight】 Official Repo for Paper ‘’HealthGPT : A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation‘’

We developed a domain-speciffc large language-vision assistant (PA-LLaVA) for pathology image understanding. Specifically, (1) we first construct a human pathology image-text dataset by cleaning the public medical image-text data for domainspecific alignment; (2) Using the proposed image-text…

This repository contains the official implementation for benchmarking various Direct Preference Optimization (DPO) methodologies on Medical Large Vision-Language Models (VLMs).

MedVH is a dataset for evaluating hallucination in large vision language models on medical visual question answering tasks, specifically with chest x-ray images. This repository provides part of the dataset, which is proposed in our paper "MedVH: Towards Systematic Evaluation of Hallucination…

Medical Multimodal LLMs

```zsh git clone --recursive https://github.com/function2-llx/MMMM.git cd MMMM mamba env create -f environment.yaml BUILDMONAI=1 pip install --no-build-isolation -e third-party/LuoLib/third-party/MONAI mamba activate mmmm echo \ "export PYTHONPATH=$PWD:$PWD/third-party/LuoLib export BUILDMONAI=1" \

LIMITR is a multi-modal representation learning model for chest X-ray images and reports. The model is based on a novel alignment scheme between the visual data and the text, which takes into account both local and global information. Furthermore, the model integrates domain-specific information…

The advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce S elf- T raining L arge L…

Authors: Hejie Cui, Lingjun Mao, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang

Welcome to the official implementation code for "Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework", accepted at CVPR2024 🎉