@article{compressingsequencesinthelatentembedding,
  title = {Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models},
  author = {Zihao Xu and John Harvill and Ziwei Fan and Yizhou Sun and Hao Ding and Hao Wang},
  year = {2026},
  eprint = {2604.15153},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.15153},
}