---
language:
- en
- zh
license: other
---
# Relation-Rich Visual Document Generator for Visual Information Extraction (RIDGE)
[![arXiv](https://img.shields.io/badge/arXiv-2504.10659-b31b1b?logo=arXiv)](https://arxiv.org/abs/2504.10659)
[![License](https://img.shields.io/badge/license-custom-blue)](./LICENSE)
[![GitHub](https://img.shields.io/badge/GitHub-code-green?logo=github)](https://github.com/AI-Application-and-Integration-Lab/RIDGE)

This is the content-driven layout generation model weight for [RIDGE](https://arxiv.org/abs/2504.10659).  
For code and usage, please visit our [GitHub](https://github.com/AI-Application-and-Integration-Lab/RIDGE).

## 📖 Citation
If you find this work useful, please cite our paper:
```
@article{jiang2025ridge,
  title={Relation-Rich Visual Document Generator for Visual Information Extraction},
  author={Jiang, Zi-Han and Lin, Chien-Wei and Li, Wei-Hua and Liu, Hsuan-Tung and Yeh, Yi-Ren and Chen, Chu-Song},
  journal={arXiv preprint arXiv:2504.10659},
  year={2025}
}
```

## 📜 License
This model is released under the **AI²Lab Source Code License (National Taiwan University)**.   
See the full license [here](./LICENSE).