@article{dynamiccompressingpromptsforefficient,
  title = {Dynamic Compressing Prompts for Efficient Inference of Large Language Models},
  author = {Jinwu Hu and Wei zhang and Yufeng Wang and Yu Hu and Bin Xiao and Mingkui Tan and Qing Du},
  year = {2025},
  eprint = {2504.11004},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.11004v1},
}