@article{enhancingandacceleratinglargelanguage,
  title = {Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression},
  author = {Haowen Hou and Fei Ma and Binwen Bai and Xinxin Zhu and Fei Yu},
  year = {2024},
  eprint = {2408.15491},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.15491v1},
}