@misc{ye2023ureader,
      title={UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model}, 
      author={Jiabo Ye and Anwen Hu and Haiyang Xu and Qinghao Ye and Ming Yan and Guohai Xu and Chenliang Li and Junfeng Tian and Qi Qian and Ji Zhang and Qin Jin and Liang He and Xin Alex Lin and Fei Huang},
      year={2023},
      eprint={2310.05126},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
@misc{ye2023mplugdocowl,
      title={mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding}, 
      author={Jiabo Ye and Anwen Hu and Haiyang Xu and Qinghao Ye and Ming Yan and Yuhao Dan and Chenlin Zhao and Guohai Xu and Chenliang Li and Junfeng Tian and Qian Qi and Ji Zhang and Fei Huang},
      year={2023},
      eprint={2307.02499},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}