@article{acceleratinglargelanguagemodelsthrough,
  title = {Accelerating Large Language Models through Partially Linear Feed-Forward Network},
  author = {Gansen Hu and Zhaoguo Wang and Jinglin Wei and Wei Huang and Haibo Chen},
  year = {2025},
  eprint = {2501.10054},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.10054v1},
}