Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.14757 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908779516264448 |
|---|---|
| author | Zhou, Kangcheng Jiang, Jun Zhang, Qing Zheng, Shuang Li, Qingli Xu, Shugong |
| author_facet | Zhou, Kangcheng Jiang, Jun Zhang, Qing Zheng, Shuang Li, Qingli Xu, Shugong |
| contents | Interpretability is significant in computational pathology, leading to the development of multimodal information integration from histopathological image and corresponding text data.However, existing multimodal methods have limited interpretability due to the lack of high-quality dataset that support explicit reasoning and inference and simple reasoning process.To address the above problems, we introduce a novel multimodal pathology large language model with strong reasoning capabilities.To improve the generation of accurate and contextually relevant textual descriptions, we design a semantic reward strategy integrated with group relative policy optimization.We construct a high-quality pathology visual question answering (VQA) dataset, specifically designed to support complex reasoning tasks.Comprehensive experiments conducted on this dataset demonstrate that our method outperforms state-of-the-art methods, even when trained with only 20% of the data.Our method also achieves comparable performance on downstream zero-shot image classification task compared with CLIP. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14757 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReinPath: A Multimodal Reinforcement Learning Approach for Pathology Zhou, Kangcheng Jiang, Jun Zhang, Qing Zheng, Shuang Li, Qingli Xu, Shugong Computer Vision and Pattern Recognition Interpretability is significant in computational pathology, leading to the development of multimodal information integration from histopathological image and corresponding text data.However, existing multimodal methods have limited interpretability due to the lack of high-quality dataset that support explicit reasoning and inference and simple reasoning process.To address the above problems, we introduce a novel multimodal pathology large language model with strong reasoning capabilities.To improve the generation of accurate and contextually relevant textual descriptions, we design a semantic reward strategy integrated with group relative policy optimization.We construct a high-quality pathology visual question answering (VQA) dataset, specifically designed to support complex reasoning tasks.Comprehensive experiments conducted on this dataset demonstrate that our method outperforms state-of-the-art methods, even when trained with only 20% of the data.Our method also achieves comparable performance on downstream zero-shot image classification task compared with CLIP. |
| title | ReinPath: A Multimodal Reinforcement Learning Approach for Pathology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.14757 |