@inproceedings{wang-etal-2026-sampkv,
    title = "{S}amp{KV}: Saliency-Aware Mixed-Precision {KV} Cache for Efficient Diffusion Language Model Inference",
    author = "Wang, Zhenrui  and
      Chang, Haodong  and
      Sui, Yang  and
      Liang, Rongjian  and
      Yuan, Bo  and
      Hu, Jiang",
    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.1968/",
    pages = "44808--44821",
    ISBN = "979-8-89176-459-0"
}