| Measuring neural net robustness with constraints O Bastani, Y Ioannou, L Lampropoulos, D Vytiniotis, A Nori, A Criminisi Advances in neural information processing systems 29, 2016 | 522 | 2016 |
| Interpreting blackbox models via model extraction O Bastani, C Kim, H Bastani arXiv preprint arXiv:1705.08504, 2017 | 416* | 2017 |
| Verifiable reinforcement learning via policy extraction O Bastani, Y Pu, A Solar-Lezama Advances in Neural Information Processing Systems, 2018 | 377 | 2018 |
| " How do I fool you?" Manipulating User Trust via Misleading Black Box Explanations H Lakkaraju, O Bastani Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 79-85, 2020 | 288 | 2020 |
| Synthesizing program input grammars O Bastani, R Sharma, A Aiken, P Liang ACM SIGPLAN Notices 52 (6), 95-110, 2017 | 229 | 2017 |
| Program synthesis using conflict-driven learning Y Feng, R Martins, O Bastani, I Dillig ACM SIGPLAN Notices 53 (4), 420-435, 2018 | 196 | 2018 |
| Vip: Towards universal visual reward and representation via value-implicit pre-training YJ Ma, S Sodhani, D Jayaraman, O Bastani, V Kumar, A Zhang The Eleventh International Conference on Learning Representations, 2023 | 192 | 2023 |
| Eureka: Human-level reward design via coding large language models YJ Ma, W Liang, G Wang, DA Huang, O Bastani, D Jayaraman, Y Zhu, ... arXiv preprint arXiv:2310.12931, 2023 | 164 | 2023 |
| Automatically learning android malware signatures from few samples Y Feng, O Bastani, R Martins, I Dillig, S Anand Proceedings of the 2017 Annual Network and Distributed System Security …, 2017 | 114* | 2017 |
| A composable specification language for reinforcement learning tasks K Jothimurugan, R Alur, O Bastani Advances in Neural Information Processing Systems 32, 2019 | 98 | 2019 |
| An efficient homomorphic encryption protocol for multi-user systems L Xiao, O Bastani, IL Yen Cryptology ePrint Archive, 2012 | 96 | 2012 |
| Algorithms for fairness in sequential decision making M Wen, O Bastani, U Topcu International Conference on Artificial Intelligence and Statistics, 1144-1152, 2021 | 93* | 2021 |
| Robust model predictive shielding for safe reinforcement learning with stochastic dynamics S Li, O Bastani 2020 IEEE International Conference on Robotics and Automation (ICRA), 7166-7172, 2020 | 91 | 2020 |
| Robust and stable black box explanations H Lakkaraju, N Arsov, O Bastani International conference on machine learning, 5628-5638, 2020 | 90 | 2020 |
| Probabilistic verification of fairness properties via concentration O Bastani, X Zhang, A Solar-Lezama Proceedings of the ACM on Programming Languages 3 (OOPSLA), 1-27, 2019 | 88 | 2019 |
| Compositional reinforcement learning from logical specifications K Jothimurugan, S Bansal, O Bastani, R Alur Advances in Neural Information Processing Systems 34, 10026-10039, 2021 | 87 | 2021 |
| Conservative offline distributional reinforcement learning Y Ma, D Jayaraman, O Bastani Advances in neural information processing systems 34, 19235-19247, 2021 | 85 | 2021 |
| Liv: Language-image representations and rewards for robotic control YJ Ma, V Kumar, A Zhang, O Bastani, D Jayaraman International Conference on Machine Learning, 23301-23320, 2023 | 74 | 2023 |
| Learning Performance-Improving Code Edits A Shypula, A Madaan, Y Zeng, U Alon, J Gardner, M Hashemi, G Neubig, ... arXiv preprint arXiv:2302.07867, 2023 | 66 | 2023 |
| Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding O Bastani American Control Conference (ACC), 2021 | 64* | 2021 |
Hamsa BastaniAssociate Professor of Operations Information and Decisions, Wharton SchoolVerified email at wharton.upenn.edu
