@inproceedings{yang-etal-2025-xquant,
    title = "{XQ}uant: Achieving Ultra-Low Bit {KV} Cache Quantization with Cross-Layer Compression",
    author = "Yang, Haoqi  and
      Yao, Yao  and
      Li, Zuchao  and
      Qi, Baoyuan  and
      Guoming, Liu  and
      Zhao, Hai",
    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.494/",
    pages = "9796--9811",
    ISBN = "979-8-89176-332-6"
}