@article{citercollaborativeinferenceforefficient,
  title = {CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing},
  author = {Wenhao Zheng and Yixiao Chen and Weitong Zhang and Souvik Kundu and Yun Li and Zhengzhong Liu and Eric P. Xing and Hongyi Wang and Huaxiu Yao},
  year = {2025},
  eprint = {2502.01976},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.01976v5},
}