| On the opportunities and risks of foundation models R Bommasani, DA Hudson, E Adeli, R Altman, S Arora, S von Arx, ... arXiv preprint arXiv:2108.07258, 2021 | 3816 | 2021 |
| Combining satellite imagery and machine learning to predict poverty N Jean, M Burke, M Xie, WM Davis, DB Lobell, S Ermon Science 353 (6301), 790-794, 2016 | 1822 | 2016 |
| Wilds: A benchmark of in-the-wild distribution shifts PW Koh, S Sagawa, H Marklund, SM Xie, M Zhang, A Balsubramani, ... International conference on machine learning, 5637-5664, 2021 | 1381 | 2021 |
| Holistic evaluation of language models P Liang, R Bommasani, T Lee, D Tsipras, D Soylu, M Yasunaga, Y Zhang, ... arXiv preprint arXiv:2211.09110, 2022 | 1059* | 2022 |
| An Explanation of In-context Learning as Implicit Bayesian Inference SM Xie, A Raghunathan, P Liang, T Ma International Conference on Learning Representations (ICLR), 2022 | 557 | 2022 |
| Transfer learning from deep features for remote sensing and poverty mapping M Xie, N Jean, M Burke, D Lobell, S Ermon AAAI, 2016 | 528 | 2016 |
| Adversarial training can hurt generalization A Raghunathan*, SM Xie*, F Yang, JC Duchi, P Liang arXiv preprint arXiv:1906.06032, 2019 | 270 | 2019 |
| Understanding and mitigating the tradeoff between robustness and accuracy A Raghunathan*, SM Xie*, F Yang, J Duchi, P Liang International Conference on Machine Learning (ICML), 2020 | 245 | 2020 |
| Weakly supervised deep learning for segmentation of remote sensing imagery S Wang, W Chen, SM Xie, G Azzari, DB Lobell Remote Sensing 12 (2), 207, 2020 | 240 | 2020 |
| Reward design with language models M Kwon, SM Xie, K Bullard, D Sadigh arXiv preprint arXiv:2303.00001, 2023 | 160 | 2023 |
| Extending the wilds benchmark for unsupervised adaptation S Sagawa, PW Koh, T Lee, I Gao, SM Xie, K Shen, A Kumar, W Hu, ... arXiv preprint arXiv:2112.05090, 2021 | 123 | 2021 |
| Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance N Jean*, SM Xie*, S Ermon Advances in Neural Information Processing Systems (NeurIPS), 2018 | 97 | 2018 |
| Data selection for language models via importance resampling SM Xie, S Santurkar, T Ma, PS Liang Advances in Neural Information Processing Systems 36, 34201-34227, 2023 | 96 | 2023 |
| Connect, not collapse: Explaining contrastive learning for unsupervised domain adaptation K Shen*, R Jones*, A Kumar*, SM Xie*, JZ HaoChen, T Ma, P Liang arXiv preprint arXiv:2204.00570, 2022 | 96 | 2022 |
| Reparameterizable Subset Sampling via Continuous Relaxations SM Xie, S Ermon IJCAI, 2019 | 88 | 2019 |
| Doremi: Optimizing data mixtures speeds up language model pretraining SM Xie, H Pham, X Dong, N Du, H Liu, Y Lu, PS Liang, QV Le, T Ma, ... Advances in Neural Information Processing Systems 36, 2023 | 87 | 2023 |
| Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning C Wei, SM Xie, T Ma Neural Information Processing Systems (NeurIPS), 2021 | 83 | 2021 |
| In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness SM Xie*, A Kumar*, R Jones*, F Khani, T Ma, P Liang International Conference on Learning Representations (ICLR), 2022 | 55 | 2022 |
| A survey on data selection for language models A Albalak, Y Elazar, SM Xie, S Longpre, N Lambert, X Wang, ... arXiv preprint arXiv:2402.16827, 2024 | 32 | 2024 |
| Same pre-training loss, better downstream: Implicit bias matters for language models H Liu, SM Xie, Z Li, T Ma International Conference on Machine Learning, 22188-22214, 2023 | 31 | 2023 |
Percy LiangAssociate Professor of Computer Science, Stanford UniversityVerified email at cs.stanford.edu
