| The Causal-Neural Connection: Expressiveness, Learnability, and Inference | Jul 2, 2021 | Causal IdentificationCausal Inference | CodeCode Available | 1 |
| UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation | Jul 2, 2021 | DecoderImage Segmentation | CodeCode Available | 1 |
| Generalization and Robustness Implications in Object-Centric Learning | Jul 1, 2021 | Inductive BiasObject | CodeCode Available | 1 |
| ResViT: Residual vision transformers for multi-modal medical image synthesis | Jun 30, 2021 | DiversityImage Generation | CodeCode Available | 1 |
| Digging Errors in NMT: Evaluating and Understanding Model Errors from Partial Hypothesis Space | Jun 29, 2021 | Data AugmentationInductive Bias | —Unverified | 0 |
| Rethinking Token-Mixing MLP for MLP-based Vision Backbone | Jun 28, 2021 | Inductive Bias | —Unverified | 0 |
| On Incorporating Inductive Biases into VAEs | Jun 25, 2021 | Inductive Bias | CodeCode Available | 0 |
| Data efficiency in graph networks through equivariance | Jun 25, 2021 | Inductive Bias | —Unverified | 0 |
| ViTAS: Vision Transformer Architecture Search | Jun 25, 2021 | Inductive BiasNeural Architecture Search | CodeCode Available | 1 |
| Video Swin Transformer | Jun 24, 2021 | Action ClassificationAction Recognition | CodeCode Available | 2 |
