@article{discoveringthegemsinearlylayers,
  title = {Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction},
  author = {Zhenmei Shi and Yifei Ming and Xuan-Phi Nguyen and YIngyu Liang and Shafiq Joty},
  year = {2024},
  eprint = {2409.17422},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.17422v1},
}