@article{cometacceleratingprivateinferencefor,
  title = {Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity},
  author = {Guang Yan and Yuhui Zhang and Zimu Guo and Lutan Zhao and Xiaojun Chen and Chen Wang and Wenhao Wang and Dan Meng and Rui Hou},
  year = {2025},
  eprint = {2505.07239},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.07239v1},
}