@inproceedings{li-etal-2026-kg,
    title = "{KG}-{V}i{P}: Bridging Knowledge Grounding and Visual Perception in Multi-modal {LLM}s for Visual Question Answering",
    author = "Li, Zhiyang  and
      Ke, Ao  and
      Cao, Yukun  and
      Xie, Xike",
    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.1622/",
    pages = "35144--35157",
    ISBN = "979-8-89176-390-6"
}