Follow
Justin Svegliato
Justin Svegliato
Senior Research Scientist, Microsoft, UC Berkeley
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
Tensor Trust: Interpretable prompt injection attacks from an online game
S Toyer, O Watkins, EA Mendes, J Svegliato, L Bailey, T Wang, I Ong, ...
12th International Conference on Learning Representations (ICLR), 2024
522024
Learning to optimize autonomy in competence-aware systems
C Basich, J Svegliato, KH Wray, S Witwicki, J Biswas, S Zilberstein
18th International Conference on Autonomous Agents and Multiagent Systems …, 2020
462020
Ethically compliant sequential decision making
J Svegliato, SB Nashed, S Zilberstein
35th AAAI Conference on Artificial Intelligence (AAAI), 2021
432021
Belief space metareasoning for exception recovery
J Svegliato, KH Wray, SJ Witwicki, J Biswas, S Zilberstein
International Conference on Intelligent Robots and Systems (IROS), 2019
372019
A StrongREJECT for empty jailbreaks
A Souly, Q Lu, D Bowen, T Trinh, E Hsieh, S Pandey, P Abbeel, ...
arXiv preprint arXiv:2402.10260, 2024
342024
Meta-level control of anytime algorithms with online performance prediction
J Svegliato, KH Wray, S Zilberstein
27th International Joint Conference of Artificial Intelligence (IJCAI), 2018
312018
A model-free approach to meta-level control of anytime algorithms
J Svegliato, P Sharma, S Zilberstein
International Conference on Robotics and Automation (ICRA), 2020
202020
Adaptive metareasoning for bounded rational agents
J Svegliato, S Zilberstein
IJCAI Workshop on Architectures and Evaluation for Generality, Autonomy and …, 2018
182018
Ethically compliant planning within moral communities
SB Nashed, J Svegliato, S Zilberstein
4th Conference on Artificial Intelligence, Ethics, and Society (AIES), 2021
172021
Tuning the hyperparameters of anytime planning: A metareasoning approach with deep reinforcement learning
A Bhatia, J Svegliato, S Nashed, S Zilberstein
32nd International Conference on Planning and Scheduling (ICAPS), 2022
142022
Active reward learning from multiple teachers
P Barnett, R Freedman, J Svegliato, S Russell
AAAI Workshop on Artificial Intelligence Safety (SafeAI), 2022
132022
On the benefits of randomly adjusting anytime weighted A*
A Bhatia, J Svegliato, S Zilberstein
14th Symposium on Combinatorial Search (SoCS), 2021
132021
Improving competence for reliable autonomy
C Basich, J Svegliato, S Zilberstein, KH Wray, SJ Witwicki
ECAI Workshop on Agents and Robots for Reliable Engineered Autonomy (AREA), 2020
132020
Solving Markov decision processes with partial state abstractions
SB Nashed, J Svegliato, M Brucato, C Basich, R Grupen, S Zilberstein
International Conference on Robotics and Automation (ICRA), 2021
122021
Metareasoning for safe decision making in autonomous systems
J Svegliato, C Basich, S Saisubramanian, S Zilberstein
International Conference on Robotics and Automation (ICRA), 2022
112022
Introspective autonomous vehicle operational management
J Svegliato, S Witwicki, KH Wray, S Zilberstein
US Patent 10,649,453, 2020
92020
An integrated approach to moral autonomous systems
J Svegliato, S Nashed, S Zilberstein
24th European Conference on Artificial Intelligence (ECAI), 2020
92020
Competence-aware systems
C Basich, J Svegliato, KH Wray, S Witwicki, J Biswas, S Zilberstein
Artificial Intelligence Journal (AIJ), 2022
82022
Tensor Trust: Interpretable prompt injection attacks from an online game (November 2023)
S Toyer, O Watkins, EA Mendes, J Svegliato, L Bailey, T Wang, I Ong, ...
arXiv preprint arXiv:2311.01011, 2024
62024
Fairness and sequential decision making: Limits, lessons, and opportunities
SB Nashed, J Svegliato, SL Blodgett
arXiv preprint arXiv:2301.05753, 2023
62023
The system can't perform the operation now. Try again later.
Articles 1–20