| CoAtNet: Marrying Convolution and Attention for All Data Sizes | Jun 9, 2021 | AllImage Classification | CodeCode Available | 1 |
| Pretrained Encoders are All You Need | Jun 9, 2021 | AllContrastive Learning | CodeCode Available | 1 |
| On Inductive Biases for Heterogeneous Treatment Effect Estimation | Jun 7, 2021 | AllHeterogeneous Treatment Effect Estimation | CodeCode Available | 1 |
| Self-Supervision is All You Need for Solving Rubik's Cube | Jun 6, 2021 | AllCombinatorial Optimization | CodeCode Available | 1 |
| Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction | Jun 3, 2021 | AllDocument-level Relation Extraction | CodeCode Available | 1 |
| Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition | May 31, 2021 | AllComputational Efficiency | CodeCode Available | 1 |
| ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction | May 21, 2021 | AllData Compression | CodeCode Available | 1 |
| Not All Memories are Created Equal: Learning to Forget by Expiring | May 13, 2021 | AllLanguage Modeling | CodeCode Available | 1 |
| MLP-Mixer: An all-MLP Architecture for Vision | May 4, 2021 | Allimage-classification | CodeCode Available | 1 |
| One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework | May 1, 2021 | AllDeep Learning | CodeCode Available | 1 |
