@inproceedings{wang-etal-2025-fier,
    title = "{FIER}: Fine-Grained and Efficient {KV} Cache Retrieval for Long-context {LLM} Inference",
    author = "Wang, Dongwei  and
      Liu, Zijie  and
      Wang, Song  and
      Ren, Yuxin  and
      Deng, Jianing  and
      Hu, Jingtong  and
      Chen, Tianlong  and
      Yang, Huanrui",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.515/",
    doi = "10.18653/v1/2025.findings-emnlp.515",
    pages = "9702--9713",
    ISBN = "979-8-89176-335-7"
}