Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.07098 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910044962947072 |
|---|---|
| author | Shui, Zhongyi Li, Honglin Ji, Xiaozhong Zhang, Ye Yang, Zijiang Zhu, Chenglu Sun, Yuxuan Yao, Kai He, Conghui Tan, Cheng |
| author_facet | Shui, Zhongyi Li, Honglin Ji, Xiaozhong Zhang, Ye Yang, Zijiang Zhu, Chenglu Sun, Yuxuan Yao, Kai He, Conghui Tan, Cheng |
| contents | Nucleus detection in histopathology is pivotal for a wide range of clinical applications. Existing approaches either regress nuclear proxy maps that require complex post-processing, or employ dense anchors or queries that introduce severe foreground-background imbalance. In this work, we reformulate nucleus detection as next-point prediction, wherein a multimodal large language model is developed to directly output foreground nucleus centroids from the input image. The model is trained in two stages. In the supervised learning stage, we propose spatial-aware soft supervision to relax strict centroid matching and a chain-of-visual-thought strategy to incorporate visual priors that facilitate coordinate prediction. In the reinforcement fine-tuning stage, we design distribution matching reward, low-variance group filtering, and fine-grained advantage shaping to further improve the model's detection quality. Extensive experiments on nine widely used benchmarks demonstrate the superiority of our method. Code will be released soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07098 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NuNext: Reframing Nucleus Detection as Next-Point Detection Shui, Zhongyi Li, Honglin Ji, Xiaozhong Zhang, Ye Yang, Zijiang Zhu, Chenglu Sun, Yuxuan Yao, Kai He, Conghui Tan, Cheng Computer Vision and Pattern Recognition Nucleus detection in histopathology is pivotal for a wide range of clinical applications. Existing approaches either regress nuclear proxy maps that require complex post-processing, or employ dense anchors or queries that introduce severe foreground-background imbalance. In this work, we reformulate nucleus detection as next-point prediction, wherein a multimodal large language model is developed to directly output foreground nucleus centroids from the input image. The model is trained in two stages. In the supervised learning stage, we propose spatial-aware soft supervision to relax strict centroid matching and a chain-of-visual-thought strategy to incorporate visual priors that facilitate coordinate prediction. In the reinforcement fine-tuning stage, we design distribution matching reward, low-variance group filtering, and fine-grained advantage shaping to further improve the model's detection quality. Extensive experiments on nine widely used benchmarks demonstrate the superiority of our method. Code will be released soon. |
| title | NuNext: Reframing Nucleus Detection as Next-Point Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07098 |