@misc{chen2024sepllm,
  title={SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator},
  author={Guoxuan Chen and Han Shi and Jiawei Li and Yihang Gao and Xiaozhe Ren and Yimeng Chen and Xin Jiang and Zhenguo Li and Weiyang Liu and Chao Huang},
  year={2024},
  eprint={2412.12094},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2412.12094}
}