| Categorical reparameterization with gumbel-softmax E Jang, S Gu, B Poole arXiv preprint arXiv:1611.01144, 2016 | 6311 | 2016 |
| Gpt-4 technical report J Achiam, S Adler, S Agarwal, L Ahmad, I Akkaya, FL Aleman, D Almeida, ... arXiv preprint arXiv:2303.08774, 2023 | 4261 | 2023 |
| Large language models are zero-shot reasoners T Kojima, SS Gu, M Reid, Y Matsuo, Y Iwasawa Advances in neural information processing systems 35, 22199-22213, 2022 | 3015 | 2022 |
| Scaling instruction-finetuned language models HW Chung, L Hou, S Longpre, B Zoph, Y Tay, W Fedus, Y Li, X Wang, ... Journal of Machine Learning Research 25 (70), 1-53, 2024 | 2582 | 2024 |
| Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates S Gu, E Holly, T Lillicrap, S Levine 2017 IEEE international conference on robotics and automation (ICRA), 3389-3396, 2017 | 1940 | 2017 |
| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023 | 1611 | 2023 |
| Continuous deep q-learning with model-based acceleration S Gu, T Lillicrap, I Sutskever, S Levine International conference on machine learning, 2829-2838, 2016 | 1299 | 2016 |
| Towards deep neural network architectures robust to adversarial examples S Gu, L Rigazio arXiv preprint arXiv:1412.5068, 2014 | 1041 | 2014 |
| Beyond the imitation game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... arXiv preprint arXiv:2206.04615, 2022 | 1033 | 2022 |
| Data-efficient hierarchical reinforcement learning O Nachum, SS Gu, H Lee, S Levine Advances in neural information processing systems 31, 2018 | 1013 | 2018 |
| A minimalist approach to offline reinforcement learning S Fujimoto, SS Gu Advances in neural information processing systems 34, 20132-20145, 2021 | 735 | 2021 |
| Dynamics-aware unsupervised discovery of skills A Sharma, S Gu, S Levine, V Kumar, K Hausman arXiv preprint arXiv:1907.01657, 2019 | 449 | 2019 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, 2024 | 412 | 2024 |
| Q-prop: Sample-efficient policy gradient with an off-policy critic S Gu, T Lillicrap, Z Ghahramani, RE Turner, S Levine arXiv preprint arXiv:1611.02247, 2016 | 407 | 2016 |
| Human-centric dialog training via offline reinforcement learning N Jaques, JH Shen, A Ghandeharioun, C Ferguson, A Lapedriza, ... arXiv preprint arXiv:2010.05848, 2020 | 402* | 2020 |
| Large language models can self-improve J Huang, SS Gu, L Hou, Y Wu, X Wang, H Yu, J Han arXiv preprint arXiv:2210.11610, 2022 | 367 | 2022 |
| Temporal difference models: Model-free deep rl for model-based control V Pong, S Gu, M Dalal, S Levine arXiv preprint arXiv:1802.09081, 2018 | 299 | 2018 |
| A divergence minimization perspective on imitation learning methods SKS Ghasemipour, R Zemel, S Gu Conference on robot learning, 1259-1277, 2020 | 297 | 2020 |
| Sequence tutor: Conservative fine-tuning of sequence generation models with kl-control N Jaques, S Gu, D Bahdanau, JM Hernández-Lobato, RE Turner, D Eck International Conference on Machine Learning, 1645-1654, 2017 | 269* | 2017 |
| Language as an abstraction for hierarchical deep reinforcement learning Y Jiang, SS Gu, KP Murphy, C Finn Advances in Neural Information Processing Systems 32, 2019 | 242 | 2019 |
Sergey LevineUC Berkeley, Physical IntelligenceVerified email at eecs.berkeley.edu
