@inproceedings{li-etal-2026-retrieval-heads,
    title = "Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models",
    author = "Li, Aaron Branson Cigres  and
      Wang, Zhaowei  and
      Zhao, Yu  and
      Du, Yiming  and
      Li, Haobo  and
      Ren, Xiyu  and
      Wong, Ginny  and
      See, Simon  and
      Luo, Lishu  and
      Duan, Haodong  and
      Minervini, Pasquale  and
      Song, Yangqiu",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1264/",
    pages = "28801--28818",
    ISBN = "979-8-89176-459-0"
}