| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, JB Alayrac, J Yu, R Soricut, J Schalkwyk, ... arXiv preprint arXiv:2312.11805, 2023 | 6995 | 2023 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... arXiv preprint arXiv:2403.05530, 2024 | 3439 | 2024 |
| Improved knowledge distillation via teacher assistant SI Mirzadeh, M Farajtabar, A Li, N Levine, A Matsukawa, H Ghasemzadeh Proceedings of the AAAI conference on artificial intelligence 34 (04), 5191-5198, 2020 | 1678 | 2020 |
| Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities G Comanici, E Bieber, M Schaekermann, I Pasupat, N Sachdeva, I Dhillon, ... arXiv preprint arXiv:2507.06261, 2025 | 1337 | 2025 |
| Challenges of real-world reinforcement learning: definitions, benchmarks and analysis G Dulac-Arnold, N Levine, DJ Mankowitz, J Li, C Paduraru, S Gowal, ... Machine Learning 110 (9), 2419-2468, 2021 | 877 | 2021 |
| An empirical investigation of the challenges of real-world reinforcement learning G Dulac-Arnold, N Levine, DJ Mankowitz, J Li, C Paduraru, S Gowal, ... arXiv preprint arXiv:2003.11881, 2020 | 190 | 2020 |
| Rotting bandits N Levine, K Crammer, S Mannor Advances in neural information processing systems 30, 2017 | 164 | 2017 |
| Robust reinforcement learning for continuous control with model misspecification DJ Mankowitz, N Levine, R Jeong, Y Shi, J Kay, A Abdolmaleki, ... arXiv preprint arXiv:1906.07516, 2019 | 151 | 2019 |
| Towards responsible development of generative AI for education: An evaluation-driven approach I Jurenka, M Kunesch, KR McKee, D Gillick, S Zhu, S Wiltberger, SM Phal, ... arXiv preprint arXiv:2407.12687, 2024 | 107 | 2024 |
| Optimization and generalization of regularization-based continual learning: a loss approximation viewpoint D Yin, M Farajtabar, A Li, N Levine, A Mott arXiv preprint arXiv:2006.10974, 2020 | 58 | 2020 |
| Shallow updates for deep reinforcement learning N Levine, T Zahavy, DJ Mankowitz, A Tamar, S Mannor Advances in Neural Information Processing Systems 30, 2017 | 55 | 2017 |
| Prediction, consistency, curvature: Representation learning for locally-linear control N Levine, Y Chow, R Shu, A Li, M Ghavamzadeh, H Bui arXiv preprint arXiv:1909.01506, 2019 | 40 | 2019 |
| Balancing constraints and rewards with meta-gradient d4pg DA Calian, DJ Mankowitz, T Zahavy, Z Xu, J Oh, N Levine, T Mann arXiv preprint arXiv:2010.06324, 2020 | 33 | 2020 |
| Task-agnostic continual learning with hybrid probabilistic models P Kirichenko, M Farajtabar, D Rao, B Lakshminarayanan, N Levine, A Li, ... arXiv preprint arXiv:2106.12772, 2021 | 28 | 2021 |
| An extended relevance model for session search N Levine, H Roitman, D Cohen Proceedings of the 40th International ACM SIGIR Conference on Research and …, 2017 | 21 | 2017 |
| A maximum-entropy approach to off-policy evaluation in average-reward MDPs N Lazic, D Yin, M Farajtabar, N Levine, D Gorur, C Harris, D Schuurmans Advances in Neural Information Processing Systems 33, 12461-12471, 2020 | 13 | 2020 |
| Robust reinforcement learning for continuous control with model misspecification DJ Mankowitz, N Levine, RC Jeong, A Abdolmaleki, JT Springenberg, ... US Patent App. 17/620,164, 2022 | 6 | 2022 |
| Neural rate control for video encoding using imitation learning H Mao, C Gu, M Wang, A Chen, N Lazic, N Levine, D Pang, R Claus, ... arXiv preprint arXiv:2012.05339, 2020 | 4 | 2020 |
| Actively learning to attract followers on Twitter N Levine, TA Mann, S Mannor arXiv preprint arXiv:1504.04114, 2015 | 3 | 2015 |
| Relevance model for session search H Roitman, D Cohen, N Levine US Patent 10,956,409, 2021 | | 2021 |
