@article{astudyonhiddenlayerdistillationforlargel,
  title = {A Study on Hidden Layer Distillation for Large Language Model Pre-Training},
  author = {Maxime Guigon and Lucas Dixon and Michaël E. Sander},
  year = {2026},
  eprint = {2605.11513},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.11513},
}