@inproceedings{zeng-etal-2024-memorize,
    title = "Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk",
    author = "Zeng, Zhiyuan  and
      Guo, Qipeng  and
      Liu, Xiaoran  and
      Yin, Zhangyue  and
      Shu, Wentao  and
      Huang, Mianqiu  and
      Wang, Bo  and
      Zhou, Yunhua  and
      Li, Linlin  and
      Liu, Qun  and
      Qiu, Xipeng",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.1169/",
    doi = "10.18653/v1/2024.emnlp-main.1169",
    pages = "21021--21034"
}