@inproceedings{liu-etal-2026-dart,
    title = "{DART}: Low-Latency Parallel Drafting with Continuity-Aware Tree Pruning for Speculative Decoding",
    author = "Liu, Fuliang  and
      Li, Xue  and
      Zhao, Ketai  and
      Gao, Yinxi  and
      Zhou, Ziyan  and
      Zhang, Zhonghui  and
      Dou, Wanchun  and
      Zhong, Sheng  and
      Wang, Zhibin  and
      Tian, Chen",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.492/",
    pages = "11316--11331",
    ISBN = "979-8-89176-459-0"
}