@article{dockylinalargemultimodalmodelforvisual,
  title = {DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming},
  author = {Jiaxin Zhang and Wentao Yang and Songxuan Lai and Zecheng Xie and Lianwen Jin},
  year = {2024},
  eprint = {2406.19101},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.19101v4},
}