@article{DBLP:journals/corr/abs-2202-08906,
  author       = {Barret Zoph and
                  Irwan Bello and
                  Sameer Kumar and
                  Nan Du and
                  Yanping Huang and
                  Jeff Dean and
                  Noam Shazeer and
                  William Fedus},
  title        = {Designing Effective Sparse Expert Models},
  journal      = {CoRR},
  volume       = {abs/2202.08906},
  year         = {2022},
  url          = {https://arxiv.org/abs/2202.08906},
  eprinttype    = {arXiv},
  eprint       = {2202.08906},
  timestamp    = {Thu, 17 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2202-08906.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

{"_id":"pycA3FSG387mnyLwL","bibbaseid":"zoph-bello-kumar-du-huang-dean-shazeer-fedus-designingeffectivesparseexpertmodels-2022","author_short":["Zoph, B.","Bello, I.","Kumar, S.","Du, N.","Huang, Y.","Dean, J.","Shazeer, N.","Fedus, W."],"bibdata":{"bibtype":"article","type":"article","author":[{"firstnames":["Barret"],"propositions":[],"lastnames":["Zoph"],"suffixes":[]},{"firstnames":["Irwan"],"propositions":[],"lastnames":["Bello"],"suffixes":[]},{"firstnames":["Sameer"],"propositions":[],"lastnames":["Kumar"],"suffixes":[]},{"firstnames":["Nan"],"propositions":[],"lastnames":["Du"],"suffixes":[]},{"firstnames":["Yanping"],"propositions":[],"lastnames":["Huang"],"suffixes":[]},{"firstnames":["Jeff"],"propositions":[],"lastnames":["Dean"],"suffixes":[]},{"firstnames":["Noam"],"propositions":[],"lastnames":["Shazeer"],"suffixes":[]},{"firstnames":["William"],"propositions":[],"lastnames":["Fedus"],"suffixes":[]}],"title":"Designing Effective Sparse Expert Models","journal":"CoRR","volume":"abs/2202.08906","year":"2022","url":"https://arxiv.org/abs/2202.08906","eprinttype":"arXiv","eprint":"2202.08906","timestamp":"Thu, 17 Aug 2023 01:00:00 +0200","biburl":"https://dblp.org/rec/journals/corr/abs-2202-08906.bib","bibsource":"dblp computer science bibliography, https://dblp.org","bibtex":"@article{DBLP:journals/corr/abs-2202-08906,\n author = {Barret Zoph and\n Irwan Bello and\n Sameer Kumar and\n Nan Du and\n Yanping Huang and\n Jeff Dean and\n Noam Shazeer and\n William Fedus},\n title = {Designing Effective Sparse Expert Models},\n journal = {CoRR},\n volume = {abs/2202.08906},\n year = {2022},\n url = {https://arxiv.org/abs/2202.08906},\n eprinttype = {arXiv},\n eprint = {2202.08906},\n timestamp = {Thu, 17 Aug 2023 01:00:00 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-2202-08906.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}\n\n","author_short":["Zoph, B.","Bello, I.","Kumar, S.","Du, N.","Huang, Y.","Dean, J.","Shazeer, N.","Fedus, W."],"key":"DBLP:journals/corr/abs-2202-08906","id":"DBLP:journals/corr/abs-2202-08906","bibbaseid":"zoph-bello-kumar-du-huang-dean-shazeer-fedus-designingeffectivesparseexpertmodels-2022","role":"author","urls":{"Paper":"https://arxiv.org/abs/2202.08906"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"http://dblp.org/pers/tb2/d/Dean:Jeffrey","dataSources":["rMEZSGRpGTSfEZaHM"],"keywords":[],"search_terms":["designing","effective","sparse","expert","models","zoph","bello","kumar","du","huang","dean","shazeer","fedus"],"title":"Designing Effective Sparse Expert Models","year":2022}