@inproceedings{zhou-etal-2026-a3,
    title = "$A^3$: Attention-Aware Accurate {KV} Cache Fusion for Fast Large Language Model Serving",
    author = "Zhou, Yuechi  and
      Su, Yi  and
      Zhang, Jianxin  and
      Xia, Qingrong  and
      Wang, Zhefeng  and
      Duan, Xinyu  and
      Huai, Baoxing  and
      Chen, Kehai  and
      Li, Juntao  and
      Zhang, Min",
    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.113/",
    pages = "2646--2661",
    ISBN = "979-8-89176-459-0"
}