VITA-Group/M3ViT
[NeurIPS 2022] “M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design”, Hanxue Liang*, Zhiwen Fan*, Rishov Sarkar, Ziyu Jiang, Tianlong Chen, Kai Zou, Yu Cheng, Cong Hao, Zhangyang Wang
PythonMIT
Stargazers
- ajestevesUniversity of Minho
- altriasjy31m78
- Annbless
- CasiaFanUIUC
- DengZeshuai
- digantamisra98@mila-iqia @landskape-ai
- dltlqqns
- eugenelawrence
- fly51flyPRIS
- GitHub30Osaka, Japan
- Hamidreza-RamezaniUniversity of British Columbia
- hanxuel
- hpismias
- JeffCarpenterCanada
- Jenhonnnnnn
- junhochoSAIT @SAITPublic
- jyhong836University of Texas at Austin
- KnightAllen
- liuajian
- lori930
- lrzniu
- LuodianNanyang Technological University
- minjoong507Seoul National University
- NizarIslahMontreal, Canada
- paulpanwangXiamen University
- prismformoreHKUST
- ruihang-chuCUHK
- sarashoouriUniversity of Michigan - Ann Arbor
- supercooledithChina
- wanganzhiChengDu
- wizyoungShanghai
- YoungBigBird1985
- YTEP-ZHI@OpenDriveLab
- ZFancyDepartment of Computer Science, HKBU
- zhiwenfan
- zhuwenzhenAWS AI