@article{dontdropdropoutoptimizinglayersparsityfo,
  title = {Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference},
  author = {Mostafa Elhoushi and Alex Pretko and Nolan Dey and Bin Claire Zhang and Gavia Gray and Gurpreet Gosal and Abdulrahman Mahmoud and Shane Bergsma and Joel Hestness},
  year = {2026},
  eprint = {2609.05275},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.05275},
}