@inproceedings{luo-etal-2025-turning,
    title = "Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling",
    author = "Luo, Xianzhen  and
      Wang, Yixuan  and
      Zhu, Qingfu  and
      Zhang, Zhiming  and
      Zhang, Xuanyu  and
      Yang, Qing  and
      Xu, Dongliang",
    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.338/",
    pages = "6816--6831",
    ISBN = "979-8-89176-251-0"
}