 Group-robust Sample Reweighting for Subpopulation Shifts via Influence FunctionsInternational Conference on Learning Representations (ICLR), 2025 |
 Upsample or Upweight? Balanced Training on Heavily Imbalanced DatasetsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary AdjustmentInternational Conference on Learning Representations (ICLR), 2024 |
 |
 Stubborn Lexical Bias in Data and ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 On the Alignment of Group Fairness with Attribute PrivacyWISE (WISE), 2022 |
 UMIX: Improving Importance Weighting for Subpopulation Shift via
Uncertainty-Aware MixupNeural Information Processing Systems (NeurIPS), 2022 |
 Pareto Invariant Risk Minimization: Towards Mitigating the Optimization
Dilemma in Out-of-Distribution GeneralizationInternational Conference on Learning Representations (ICLR), 2022 |
