| | --- |
| | license: apache-2.0 |
| | datasets: |
| | - foreverbeliever/OmniMedVQA |
| | language: |
| | - en |
| | metrics: |
| | - accuracy |
| | base_model: |
| | - Qwen/Qwen2-VL-2B-Instruct |
| | pipeline_tag: visual-question-answering |
| | --- |
| | # Med-R1 |
| | Med-R1 is a reinforcement learning (RL)-enhanced vision-language model (VLM) designed for medical reasoning across 8 imaging modalities (CT, MRI, Ultrasound, Dermoscopy, Fundus Photography, Optical Coherence Tomography (OCT), Microscopy, and X-ray) and 5 key tasks (modality recognition, anatomy identification, disease diagnosis, lesion grading, and biological attribute analysis). Using Group Relative Policy Optimization (GRPO), Med-R1 improves generalization and trustworthiness, surpassing Qwen2-VL-2B by 29.94% and even outperforming the much larger Qwen2-VL-72B. Our model checkpoints provide researchers with a powerful tool for advancing medical AI with RL-driven enhancements. |
| |
|
| | ## Description of Models |
| |
|
| | - **Cross-Modality**: We provide checkpoints trained separately on the following modalities: |
| | - **CT**, **MRI**, **X-Ray**, **Fundus (FP)**, **Dermoscopy (Der)**, **Microscopy (Micro)**, **OCT**, and **Ultrasound (US)**. |
| |
|
| | - **Cross-Task Learning**: We provide checkpoints trained separately on the following tasks: |
| | - **Anatomy Identification**, **Disease Diagnosis**, **Lesion Grading**, **Modality Recognition**, and **Biological Attribute Analysis**. |
| |
|
| | ## Citation |
