---
tags:
- pytorch
- pathology
- flow-matching
- dit
pipeline_tag: unconditional-image-generation
---

This model provides the **pretrained DiT backbone for Agent-GenPath**, supporting pathology image synthesis and downstream segmentation.

The model is introduced in the following paper:

**Agent-Driven Generative Priors for Pathology Image Synthesis and Segmentation**

arXiv: [**2611.06701**](https://arxiv.org/abs/2611.06701) | [PDF](https://arxiv.org/pdf/2611.06701)

Code: [**https://github.com/script-Yang/Agent-GenPath**](https://github.com/script-Yang/Agent-GenPath)

## Citation

```bibtex
@misc{yang2026agentdrivengenerativepriorspathology,
      title={Agent-Driven Generative Priors for Pathology Image Synthesis and Segmentation},
      author={Sicheng Yang and Rui Tang and Haipeng Zhou and Hongqiu Wang and Zhaohu Xing and Jianda Ma and Lie Dai and Guang Yang and Lei Zhu},
      year={2026},
      eprint={2611.06701},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2611.06701},
}
```