@inproceedings{wang-etal-2024-mementos,
    title = "Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences",
    author = "Wang, Xiyao  and
      Zhou, Yuhang  and
      Liu, Xiaoyu  and
      Lu, Hongjin  and
      Xu, Yuancheng  and
      He, Feihong  and
      Yoon, Jaehong  and
      Lu, Taixi  and
      Liu, Fuxiao  and
      Bertasius, Gedas  and
      Bansal, Mohit  and
      Yao, Huaxiu  and
      Huang, Furong",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.25/",
    doi = "10.18653/v1/2024.acl-long.25",
    pages = "416--442"
}