@article{llavarenhancedvisualinstructiontuningfor,
  title = {LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding},
  author = {Yanzhe Zhang and Ruiyi Zhang and Jiuxiang Gu and Yufan Zhou and Nedim Lipka and Diyi Yang and Tong Sun},
  year = {2023},
  eprint = {2306.17107},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.17107v2},
}