@inproceedings{li-etal-2024-mvp,
    title = "{MVP}-Bench: Can Large Vision-Language Models Conduct Multi-level Visual Perception Like Humans?",
    author = "Li, Guanzhen  and
      Xie, Yuxi  and
      Kan, Min-Yen",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.789/",
    doi = "10.18653/v1/2024.findings-emnlp.789",
    pages = "13505--13527"
}