Sotabase

Career

· Research Assistant Professor, University of Pennsylvania2018–2022
· Postdoctoral Researcher, Massachusetts Institute of Technology (MIT)2017–2018
· PhD in Computer Science, Stanford University2012–2018
· A.B. in Mathematics, Harvard University2008–2012
· UPenn

Publications (326)

DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Robotics: Science and Systems · 2024
512
cited
Eureka: Human-Level Reward Design via Coding Large Language Models
International Conference on Learning Representations · 2023
488
cited
Measuring Neural Net Robustness with Constraints
Neural Information Processing Systems · 2016
445
cited
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
International Conference on Learning Representations · 2022
393
cited
Verifiable Reinforcement Learning via Policy Extraction
Neural Information Processing Systems · 2018
370
cited
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration
IEEE International Conference on Robotics and Automation · 2024
282
cited
"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations
AAAI/ACM Conference on AI, Ethics, and Society · 2019
278
cited
Synthesizing program input grammars
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2016
194
cited
LIV: Language-Image Representations and Rewards for Robotic Control
International Conference on Machine Learning · 2023
184
cited
Interpreting Blackbox Models via Model Extraction
arXiv.org · 2017
183
cited
Program synthesis using conflict-driven learning
ACM-SIGPLAN Symposium on Programming Language Design and Implementation · 2017
178
cited
Interpretability via Model Extraction
arXiv.org · 2017
135
cited
A Composable Specification Language for Reinforcement Learning Tasks
Neural Information Processing Systems · 2020
103
cited
Automated Synthesis of Semantic Malware Signatures using Maximum Satisfiability
Network and Distributed System Security Symposium · 2016
103
cited
Conservative Offline Distributional Reinforcement Learning
Neural Information Processing Systems · 2021
100
cited
Compositional Reinforcement Learning from Logical Specifications
Neural Information Processing Systems · 2021
98
cited
Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics
IEEE International Conference on Robotics and Automation · 2019
97
cited
Robust and Stable Black Box Explanations
International Conference on Machine Learning · 2020
92
cited
Probabilistic verification of fairness properties via concentration
Proc. ACM Program. Lang. · 2018
78
cited
How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regression
Neural Information Processing Systems · 2022
76
cited
Sotabase
Osbert Bastani | Researcher Profile | Sotabase | Sotabase