@inproceedings{ni-etal-2025-ems,
    title = "{EMS}-{SD}: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models",
    author = "Ni, Yunsheng  and
      Liu, Chuanjian  and
      Tang, Yehui  and
      Han, Kai  and
      Wang, Yunhe",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-long.471/",
    pages = "9307--9320",
    ISBN = "979-8-89176-189-6"
}