If you find our work helpful, please consider citing our papers 📝 and liking this project ❤️！
bib
1@article{wei2024general,
2 title={General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model},
3 author={Wei, Haoran and Liu, Chenglong and Chen, Jinyue and Wang, Jia and Kong, Lingyu and Xu, Yanming and Ge, Zheng and Zhao, Liang and Sun, Jianjian and Peng, Yuang and others},
4 journal={arXiv preprint arXiv:2409.01704},
5 year={2024}
6}
7@article{liu2024focus,
8 title={Focus Anywhere for Fine-grained Multi-page Document Understanding},
9 author={Liu, Chenglong and Wei, Haoran and Chen, Jinyue and Kong, Lingyu and Ge, Zheng and Zhu, Zining and Zhao, Liang and Sun, Jianjian and Han, Chunrui and Zhang, Xiangyu},
10 journal={arXiv preprint arXiv:2405.14295},
11 year={2024}
12}
13@article{wei2023vary,
14 title={Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models},
15 author={Wei, Haoran and Kong, Lingyu and Chen, Jinyue and Zhao, Liang and Ge, Zheng and Yang, Jinrong and Sun, Jianjian and Han, Chunrui and Zhang, Xiangyu},
16 journal={arXiv preprint arXiv:2312.06109},
17 year={2023}
18}
