@inproceedings{ijcai2025p913,
  title     = {Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information},
  author    = {Park, Seungcheol and Lee, Sojin and Kim, Jongjin and 	 Lee, Jinsik and 	 Jo, Hyunjik and Kang, U},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {8213--8221},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/913},
  url       = {https://doi.org/10.24963/ijcai.2025/913},
}