@article{mvpbenchcanlargevisionlanguagemodels,
  title = {MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?},
  author = {Guanzhen Li and Yuxi Xie and Min-Yen Kan},
  year = {2024},
  eprint = {2410.04345},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.04345v1},
}