@inproceedings{zhou-etal-2023-rome,
    title = "{ROME}: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense",
    author = "Zhou, Kankan  and
      Lai, Eason  and
      Yeong, Wei Bin Au  and
      Mouratidis, Kyriakos  and
      Jiang, Jing",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.findings-emnlp.683/",
    doi = "10.18653/v1/2023.findings-emnlp.683",
    pages = "10185--10197"
}