@inproceedings{wu-etal-2026-ven,
    title = "{VEN}-{VL}: A Visual Ensemble {M}o{E} Framework for Effective and Efficient Multi-Modal Understanding",
    author = "Wu, Yinghao  and
      Luo, Zhuoyan  and
      Yu, Yiyao  and
      Yu, Zhaojian  and
      Yang, Yujiu  and
      Zhang, Xiao-Ping",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1081/",
    pages = "22906--22920",
    ISBN = "979-8-89176-462-0"
}