@article{feng2023unidoc,
  title={UniDoc: A universal large multimodal model for simultaneous text detection, recognition, spotting and understanding},
  author={Feng, Hao and Wang, Zijian and Tang, Jingqun and Lu, Jinghui and Zhou, Wengang and Li, Houqiang and Huang, Can},
  journal={arXiv preprint arXiv:2308.11592},
  year={2023}
}