@inproceedings{wu-etal-2025-tokenselect,
    title = "{T}oken{S}elect: Efficient Long-Context Inference and Length Extrapolation for {LLM}s via Dynamic Token-Level {KV} Cache Selection",
    author = "Wu, Wei  and
      Pan, Zhuoshi  and
      Fu, Kun  and
      Wang, Chao  and
      Chen, Liyi  and
      Bai, Yunchu  and
      Wang, Tianfu  and
      Wang, Zheng  and
      Xiong, Hui",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1079/",
    pages = "21275--21292",
    ISBN = "979-8-89176-332-6"
}