@article{benchmarkingmultiimageunderstandingin,
  title = {Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning},
  author = {Bingchen Zhao and Yongshuo Zong and Letian Zhang and Timothy Hospedales},
  year = {2024},
  eprint = {2406.12742},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.12742v1},
}