@inproceedings{wang-etal-2025-inserter,
    title = "{I}n{S}erter: Speech Instruction Following with Unsupervised Interleaved Pre-training",
    author = "Wang, Dingdong  and
      Xu, Jin  and
      Chu, Ruihang  and
      Guo, Zhifang  and
      Wang, Xiong  and
      Wu, Jincenzi  and
      Yang, Dongchao  and
      Ji, Shengpeng  and
      Lin, Junyang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.882/",
    pages = "18024--18046",
    ISBN = "979-8-89176-251-0"
}