| Openai o1 system card A Jaech, A Kalai, A Lerer, A Richardson, A El-Kishky, A Low, A Helyar, ... arXiv preprint arXiv:2412.16720, 2024 | 1518 | 2024 |
| The landscape of empirical risk for nonconvex losses S Mei, Y Bai, A Montanari The Annals of Statistics 46 (6A), 2747-2774, 2018 | 416 | 2018 |
| Transformers as statisticians: Provable in-context learning with in-context algorithm selection Y Bai, F Chen, H Wang, C Xiong, S Mei Advances in neural information processing systems 36, 57125-57211, 2023 | 332 | 2023 |
| Negative preference optimization: From catastrophic collapse to effective unlearning R Zhang, L Lin, Y Bai, S Mei arXiv preprint arXiv:2404.05868, 2024 | 306 | 2024 |
| Policy finetuning: Bridging sample-efficient offline and online reinforcement learning T Xie, N Jiang, H Wang, C Xiong, Y Bai Advances in neural information processing systems 34, 27395-27407, 2021 | 242 | 2021 |
| Provable self-play algorithms for competitive reinforcement learning Y Bai, C Jin International conference on machine learning, 551-560, 2020 | 228 | 2020 |
| gpt-oss-120b & gpt-oss-20b model card S Agarwal, L Ahmad, J Ai, S Altman, A Applebaum, E Arbus, RK Arora, ... arXiv preprint arXiv:2508.10925, 2025 | 191 | 2025 |
| Near-Optimal Reinforcement Learning with Self-Play Y Bai, C Jin, T Yu Advances in Neural Information Processing Systems, 2020, 2020 | 186 | 2020 |
| A sharp analysis of model-based reinforcement learning with self-play Q Liu, T Yu, Y Bai, C Jin International Conference on Machine Learning, 7001-7010, 2021 | 183 | 2021 |
| Beyond linearization: On quadratic and higher-order approximation of wide neural networks Y Bai, JD Lee International Conference on Learning Representations (ICLR) 2020, 2019 | 154 | 2019 |
| Proxquant: Quantized neural networks via proximal operators Y Bai, YX Wang, E Liberty International Conference on Learning Representations (ICLR) 2019, 2018 | 151 | 2018 |
| When can we learn general-sum Markov games with a large number of players sample-efficiently? Z Song, S Mei, Y Bai International Conference on Learning Representations (ICLR) 2022, 2021 | 137 | 2021 |
| Provably Efficient Q-Learning with Low Switching Cost Y Bai, T Xie, N Jiang, YX Wang Advances in Neural Information Processing Systems, 2019, 2019 | 132 | 2019 |
| The role of coverage in online reinforcement learning T Xie, DJ Foster, Y Bai, N Jiang, SM Kakade arXiv preprint arXiv:2210.04157, 2022 | 110 | 2022 |
| Near-optimal provable uniform convergence in offline policy evaluation for reinforcement learning M Yin, Y Bai, YX Wang International Conference on Artificial Intelligence and Statistics, 1567-1575, 2021 | 109* | 2021 |
| How important is the train-validation split in meta-learning? Y Bai, M Chen, P Zhou, T Zhao, J Lee, S Kakade, H Wang, C Xiong International Conference on Machine Learning, 543-553, 2021 | 103 | 2021 |
| Improved online conformal prediction via strongly adaptive online learning A Bhatnagar, H Wang, C Xiong, Y Bai International Conference on Machine Learning, 2337-2363, 2023 | 100 | 2023 |
| Approximability of discriminators implies diversity in GANs Y Bai, T Ma, A Risteski International Conference on Learning Representations (ICLR) 2019, 2018 | 97 | 2018 |
| Sample-efficient learning of stackelberg equilibria in general-sum games Y Bai, C Jin, H Wang, C Xiong Advances in Neural Information Processing Systems 34, 25799-25811, 2021 | 94 | 2021 |
| How do transformers learn in-context beyond simple functions? a case study on learning with representations T Guo, W Hu, S Mei, H Wang, C Xiong, S Savarese, Y Bai arXiv preprint arXiv:2310.10616, 2023 | 88 | 2023 |
Song MeiAssistant Professor at UC BerkeleyVerified email at berkeley.edu
