• Code release: https://github.com/microsoft/torchscale
• Sep 2022: accepted by NeurIPS 2022
• April 2022: release preprint of X-MoE - On the Representation Collapse of Sparse Mixture of Experts

@inproceedings{xmoe,
  title={On the Representation Collapse of Sparse Mixture of Experts},
  author={Zewen Chi and Li Dong and Shaohan Huang and Damai Dai and Shuming Ma and Barun Patra and Saksham Singhal and Payal Bajaj and Xia Song and Xian-Ling Mao and Heyan Huang and Furu Wei},
  booktitle={Advances in Neural Information Processing Systems},
  year={2022},
  url={https://openreview.net/forum?id=mWaYC6CZf5}
}