| The Privacy Onion Effect: Memorization is Relative | Jun 21, 2022 | Machine UnlearningMemorization | CodeCode Available | 0 |
| Fewer Errors, but More Stereotypes? The Effect of Model Size on Gender Bias | Jun 20, 2022 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
| Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence | Jun 16, 2022 | Generalization BoundsMemorization | —Unverified | 0 |
| Memorization-Dilation: Modeling Neural Collapse Under Label Noise | Jun 11, 2022 | Memorization | CodeCode Available | 0 |
| Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models | Jun 9, 2022 | Common Sense ReasoningMath | CodeCode Available | 4 |
| Privacy Leakage in Text Classification: A Data Extraction Approach | Jun 9, 2022 | ClassificationMemorization | —Unverified | 0 |
| Learning to generate imaginary tasks for improving generalization in meta-learning | Jun 9, 2022 | image-classificationImage Classification | —Unverified | 0 |
| Large Loss Matters in Weakly Supervised Multi-Label Classification | Jun 8, 2022 | ClassificationMemorization | CodeCode Available | 1 |
| MSR: Making Self-supervised learning Robust to Aggressive Augmentations | Jun 4, 2022 | MemorizationSelf-Supervised Learning | —Unverified | 0 |
| White-box Membership Attack Against Machine Learning Based Retinopathy Classification | May 30, 2022 | BIG-bench Machine LearningInference Attack | —Unverified | 0 |
