@inproceedings{wang-etal-2025-longllava,
    title = "{L}ong{LL}a{VA}: Scaling Multi-modal {LLM}s to 1000 Images Efficiently via a Hybrid Architecture",
    author = "Wang, Xidong  and
      Song, Dingjie  and
      Chen, Shunian  and
      Chen, Junying  and
      Cai, Zhenyang  and
      Zhang, Chen  and
      Sun, Lichao  and
      Wang, Benyou",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1168/",
    doi = "10.18653/v1/2025.findings-emnlp.1168",
    pages = "21419--21436",
    ISBN = "979-8-89176-335-7"
}