@article{visualcroppingimproveszeroshotquestion,
  title = {Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs},
  author = {Jiarui Zhang and Mahyar Khayatkhoei and Prateek Chhikara and Filip Ilievski},
  year = {2023},
  eprint = {2310.16033},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.16033v3},
}