 Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class HierarchyInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2025 |
 Leveraging Unlabeled Data to Track MemorizationInternational Conference on Learning Representations (ICLR), 2022 |
 Multi-scale Feature Learning Dynamics: Insights for Double DescentInternational Conference on Machine Learning (ICML), 2021 |
