@inproceedings{li-etal-2024-multimodal-arxiv,
    title = "Multimodal {A}r{X}iv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models",
    author = "Li, Lei  and
      Wang, Yuqi  and
      Xu, Runxin  and
      Wang, Peiyi  and
      Feng, Xiachong  and
      Kong, Lingpeng  and
      Liu, Qi",
    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://preview.aclanthology.org/fix-sig-urls/2024.acl-long.775/",
    doi = "10.18653/v1/2024.acl-long.775",
    pages = "14369--14387"
}