@article{doccobenhancingmultimodaldocument,
  title = {Doc-CoB: Enhancing Multi-Modal Document Understanding with Visual Chain-of-Boxes Reasoning},
  author = {Ye Mo and Zirui Shao and Kai Ye and Xianwei Mao and Bo Zhang and Hangdi Xing and Peng Ye and Gang Huang and Kehan Chen and Zhou Huan and Zixu Yan and Sheng Zhou},
  year = {2025},
  eprint = {2505.18603},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.18603v1},
}