GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915223902879744 |
|---|---|
| author | Su, Yanzhou Li, Tianbin Liu, Jiyao Ma, Chenglong Ning, Junzhi Tang, Cheng Ju, Sibo Ye, Jin Chen, Pengcheng Hu, Ming Tang, Shixiang Liu, Lihao Fu, Bin Shao, Wenqi Hu, Xiaowei Liao, Xiangwen Ji, Yuanfeng He, Junjun |
| author_facet | Su, Yanzhou Li, Tianbin Liu, Jiyao Ma, Chenglong Ning, Junzhi Tang, Cheng Ju, Sibo Ye, Jin Chen, Pengcheng Hu, Ming Tang, Shixiang Liu, Lihao Fu, Bin Shao, Wenqi Hu, Xiaowei Liao, Xiangwen Ji, Yuanfeng He, Junjun |
| contents | Recent advances in general medical AI have made significant strides, but existing models often lack the reasoning capabilities needed for complex medical decision-making. This paper presents GMAI-VL-R1, a multimodal medical reasoning model enhanced by reinforcement learning (RL) to improve its reasoning abilities. Through iterative training, GMAI-VL-R1 optimizes decision-making, significantly boosting diagnostic accuracy and clinical support. We also develop a reasoning data synthesis method, generating step-by-step reasoning data via rejection sampling, which further enhances the model's generalization. Experimental results show that after RL training, GMAI-VL-R1 excels in tasks such as medical image diagnosis and visual question answering. While the model demonstrates basic memorization with supervised fine-tuning, RL is crucial for true generalization. Our work establishes new evaluation benchmarks and paves the way for future advancements in medical reasoning models. Code, data, and model will be released at \href{https://github.com/uni-medical/GMAI-VL-R1}{this link}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01886 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning Su, Yanzhou Li, Tianbin Liu, Jiyao Ma, Chenglong Ning, Junzhi Tang, Cheng Ju, Sibo Ye, Jin Chen, Pengcheng Hu, Ming Tang, Shixiang Liu, Lihao Fu, Bin Shao, Wenqi Hu, Xiaowei Liao, Xiangwen Ji, Yuanfeng He, Junjun Computer Vision and Pattern Recognition Recent advances in general medical AI have made significant strides, but existing models often lack the reasoning capabilities needed for complex medical decision-making. This paper presents GMAI-VL-R1, a multimodal medical reasoning model enhanced by reinforcement learning (RL) to improve its reasoning abilities. Through iterative training, GMAI-VL-R1 optimizes decision-making, significantly boosting diagnostic accuracy and clinical support. We also develop a reasoning data synthesis method, generating step-by-step reasoning data via rejection sampling, which further enhances the model's generalization. Experimental results show that after RL training, GMAI-VL-R1 excels in tasks such as medical image diagnosis and visual question answering. While the model demonstrates basic memorization with supervised fine-tuning, RL is crucial for true generalization. Our work establishes new evaluation benchmarks and paves the way for future advancements in medical reasoning models. Code, data, and model will be released at \href{https://github.com/uni-medical/GMAI-VL-R1}{this link}. |
| title | GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.01886 |