@inproceedings{cho-etal-2025-lossless,
    title = "Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding",
    author = "Cho, Sukmin  and
      Choi, Sangjin  and
      Hwang, Taeho  and
      Seo, Jeongyeon  and
      Jeong, Soyeong  and
      Lee, Huije  and
      Song, Hoyun  and
      Park, Jong C.  and
      Kwon, Youngjin",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.findings-naacl.216/",
    pages = "3895--3911",
    ISBN = "979-8-89176-195-7"
}