@inproceedings{xu-etal-2026-compressing,
    title = "Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models",
    author = "Xu, Zihao  and
      Harvill, John  and
      Fan, Ziwei  and
      Sun, Yizhou  and
      Ding, Hao  and
      Wang, Hao",
    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.19/",
    pages = "419--429",
    ISBN = "979-8-89176-459-0"
}