@inproceedings{hu-etal-2026-seer,
    title = "Seer: Efficient {KV} Cache Management for {LLM} Acceleration via Mitigating Semantic Search Inefficiency",
    author = "Hu, Yiwei  and
      Liu, Fangxin  and
      Liang, Yue  and
      Wang, Xuan  and
      Li, Cheng  and
      Li, Gezi  and
      Jiang, Li  and
      Guan, Haibing",
    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.1852/",
    pages = "42117--42130",
    ISBN = "979-8-89176-459-0"
}