Paperverse
The papers that
shaped deep learning.
Influential research, distilled into short summaries.
Attention Is All You Need Transformer Architecture Research Paper
NeurIPS
2017Vaswani, Shazeer, Parmar, Uszkoreit + 4 more
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The Transformer relies entirely on an attention mechanism to draw global dependencies between input and output.
100k+ CitationsRead summary
LOADING
LOADING
Paperverse
The papers that
shaped deep learning.
Influential research, distilled into short summaries.
Attention Is All You Need Transformer Architecture Research Paper
Vaswani et al.The dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The Transformer relies entirely on an attention mechanism to draw global dependencies between input and output.
100k+ Citations2017
LOADING
LOADING