[112] RoFormer: Enhanced Transformer with Rotary Position Embedding

2023λ…„ 4μ›” 26일 Β· 1 λΆ„ Β· long8v Β· 

[55] Position Prediction as an Effective Pretraining Strategy

2022λ…„ 8μ›” 26일 Β· 1 λΆ„ Β· long8v Β· 

[4] Conditional Positional Encodings for Vision Transformers

2022λ…„ 1μ›” 12일 Β· 1 λΆ„ Β· long8v Β·