%0 Journal Article %1 journals/corr/abs-2404-05089 %A Muzio, Alexandre %A Sun, Alex %A He, Churan %D 2024 %J CoRR %K dblp %T SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts. %U http://dblp.uni-trier.de/db/journals/corr/corr2404.html#abs-2404-05089 %V abs/2404.05089

@article{journals/corr/abs-2404-05089, added-at = {2024-05-15T00:00:00.000+0200}, author = {Muzio, Alexandre and Sun, Alex and He, Churan}, biburl = {https://www.bibsonomy.org/bibtex/2bef53903516b4eeea014949b3356dc1c/dblp}, ee = {https://doi.org/10.48550/arXiv.2404.05089}, interhash = {c068789ef4f352dd54de9bbc9e7712a8}, intrahash = {bef53903516b4eeea014949b3356dc1c}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-05-20T07:10:42.000+0200}, title = {SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2404.html#abs-2404-05089}, volume = {abs/2404.05089}, year = 2024 }