| PDF Link | Date | Description | Essential |
|---|---|---|---|
| Layer Normalization | July 2016 | LayerNorm | |
| Attention Is All You Need | December 2017 | Transformer | |
| Learning in High Dimension Always Amounts to Extrapolation | October 2021 | I love this one. | |
| Masked Autoencoders Are Scalable Vision Learners | December 2021 | MAE: Masked Autoencoder |