@article{trainingcommunicationefficientmixtureofe,
  title = {Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration},
  author = {Simeng Sun and Roger Waleffe},
  year = {2026},
  eprint = {2608.28511},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.28511},
}