@inproceedings{ma-etal-2026-m3,
    title = "M$^3$-{VQA}: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering",
    author = "Ma, Jiatong  and
      Guo, Longteng  and
      Liu, Yuchen  and
      Zhao, Zijia  and
      Hao, Dongze  and
      Lin, Xuanxu  and
      Liu, Jing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1888/",
    pages = "40633--40669",
    ISBN = "979-8-89176-390-6"
}