@article{densetrainingsparseinferencerethinking,
  title = {Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models},
  author = {Bowen Pan and Yikang Shen and Haokun Liu and Mayank Mishra and Gaoyuan Zhang and Aude Oliva and Colin Raffel and Rameswar Panda},
  year = {2024},
  eprint = {2404.05567},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.05567v1},
}