| Investigating Why Contrastive Learning Benefits Robustness Against Label Noise Y Xue, K Whitecross, B Mirzasoleiman International Conference on Machine Learning, 2022 | 57 | 2022 |
| Toward Understanding the Influence of Individual Clients in Federated Learning Y Xue, C Niu, Z Zheng, S Tang, C Lv, F Wu, G Chen Proceedings of the AAAI Conference on Artificial Intelligence 35 (12), 10560 …, 2021 | 46 | 2021 |
| Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression Y Xue, S Joshi, E Gan, PY Chen, B Mirzasoleiman International Conference on Machine Learning, 2023 | 18 | 2023 |
| Towards Mitigating Spurious Correlations in the Wild: A Benchmark & a more Realistic Dataset S Joshi, Y Yang, Y Xue, W Yang, B Mirzasoleiman arXiv preprint arXiv:2306.11957, 2023 | 16 | 2023 |
| Few-shot Adaption to Distribution Shifts By Mixing Source and Target Embeddings Y Xue, A Payani, Y Yang, B Mirzasoleiman arXiv preprint arXiv:2305.14521, 2023 | 11* | 2023 |
| Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift Y Xue, S Joshi, D Nguyen, B Mirzasoleiman The Twelfth International Conference on Learning Representations, 2023 | 9 | 2023 |
| Investigating the Benefits of Projection Head for Representation Learning Y Xue, E Gan, J Ni, S Joshi, B Mirzasoleiman The Twelfth International Conference on Learning Representations, 2023 | 7 | 2023 |
| Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise Y Xue, K Whitecross, B Mirzasoleiman arXiv preprint arXiv:2208.08003, 2022 | 4* | 2022 |
| Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions Y Xue, J Li, B Mirzasoleiman arXiv preprint arXiv:2502.00620, 2025 | | 2025 |