DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming

Zhang et al. "DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I9.33076

[Zhang et al. "DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/zhang2025aaai-dockylin/) doi:10.1609/AAAI.V39I9.33076

@inproceedings{zhang2025aaai-dockylin,
  title     = {{DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming}},
  author    = {Zhang, Jiaxin and Yang, Wentao and Lai, Songxuan and Xie, Zecheng and Jin, Lianwen},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {9923-9932},
  doi       = {10.1609/AAAI.V39I9.33076},
  url       = {https://mlanthology.org/aaai/2025/zhang2025aaai-dockylin/}
}