@article{seermoesparseexpertefficiencythrough,
  title = {SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts},
  author = {Alexandre Muzio and Alex Sun and Churan He},
  year = {2024},
  eprint = {2404.05089},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.05089v1},
}