@inproceedings{wang-etal-2026-scenealign,
    title = "{S}cene{A}lign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes",
    author = "Wang, Chuhan  and
      Li, Xintong  and
      Zhang, Jennifer Yuntong  and
      Wu, Junda  and
      Huang, Chengkai  and
      Yao, Lina  and
      McAuley, Julian  and
      Shang, Jingbo",
    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.779/",
    pages = "17136--17150",
    ISBN = "979-8-89176-390-6"
}