@inproceedings{fastslm2025,
  title = {Fast-SLM: Towards Latency-Optimal Hybrid Small Language Models},
  author = {Fu, Yonggan and Dong, Xin and Diao, Shizhe and Van Keirsbilck, Matthijs and Ye, Hanrong and Byeon, Wonmin and Karnati, Yashaswi and Liebenwein, Lucas and Khadkevich, Maksim and Keller, Alexander and Kautz, Jan and Lin, Yingyan Celine and Molchanov, Pavlo},
  year = {2025},
  month = {December},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  eprint = {2511.18890},
  archiveprefix = {arxiv},
}