[60] Efficient Sparsely Activated Transformers

2022λ…„ 9μ›” 2일 Β· 1 λΆ„ Β· long8v Β· 

[57] Learning Transferable Architectures for Scalable Image Recognition

2022λ…„ 8μ›” 30일 Β· 1 λΆ„ Β· long8v Β·