@inproceedings{zhu-etal-2024-vislinginstruct,
    title = "{V}is{L}ing{I}nstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization",
    author = "Zhu, Dongsheng  and
      Tang, Daniel  and
      Han, Weidong  and
      Lu, Jinghui  and
      Zhao, Yukun  and
      Xing, Guoliang  and
      Wang, Junfeng  and
      Yin, Dawei",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.naacl-long.117/",
    doi = "10.18653/v1/2024.naacl-long.117",
    pages = "2122--2135"
}