EconBase
← All authors

Julie Shah

Massachusetts Institute of Technology (from arXiv:2409.05798, 2024) · ORCID · OpenAlex

14 papers in scope · 13 published · 1 on the econ.EM arXiv · 403 citations · h-index 11 (over the papers listed here)

Papers

(1 of 14)

Enhancing Preference-based Linear Bandits via Human Response Time
working paper2024 · arXiv
with Li Shen, Yuyang Zhang, Zhaolin Ren, Claire Liang, Na Li, C. H. Liang
Paper profile arXiv arXiv:2409.05798
The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications
published2023 · Proceedings of the AAAI Conference on Artificial Intelligence · 44 citations
with Serena Booth, W. Bradley Knox, Scott Niekum, Peter Stone, Alessandro Allievi
Proceedings of the AAAI Conference on Artificial Intelligence
An Empirical Study of Reward Explanations With Human-Robot Interaction Applications
published2022 · IEEE Robotics and Automation Letters · 17 citations
with Lindsay Sanneman
IEEE Robotics and Automation Letters
Do Feature Attribution Methods Correctly Attribute Features?
published2022 · Proceedings of the AAAI Conference on Artificial Intelligence · 86 citations · first circulated 2021
with Yilun Zhou, Serena Booth, Marco Túlio Ribeiro
Proceedings of the AAAI Conference on Artificial Intelligence
Set-Based State Estimation With Probabilistic Consistency Guarantee Under Epistemic Uncertainty
published2022 · IEEE Robotics and Automation Letters · 10 citations · first circulated 2021
with Shen Li, Theodoros Stouraitis, Michael Gienger, Sethu Vijayakumar
IEEE Robotics and Automation Letters
ExSum: From Local Explanations to Model Understanding
published2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · 12 citations
with Yilun Zhou, Marco Túlio Ribeiro
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example
published2021 · Proceedings of the AAAI Conference on Artificial Intelligence · 13 citations · first circulated 2020
with Serena Booth, Yilun Zhou, Ankit Shah
Proceedings of the AAAI Conference on Artificial Intelligence
Learning Models of Sequential Decision-Making with Partial Specification of Agent Behavior
published2019 · Proceedings of the AAAI Conference on Artificial Intelligence · 17 citations
with Vaibhav Unhelkar
Proceedings of the AAAI Conference on Artificial Intelligence
Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution
published2019 · Proceedings of the AAAI Conference on Artificial Intelligence · 16 citations
with Ramya Ramakrishnan, Ece Kamar, Besmira Nushi, Debadeepta Dey, Eric Horvitz
Proceedings of the AAAI Conference on Artificial Intelligence
Collaborative Planning with Encoding of Users' High-Level Strategies
published2017 · Proceedings of the AAAI Conference on Artificial Intelligence · 35 citations
with Joseph Kim, Christopher Banks
Proceedings of the AAAI Conference on Artificial Intelligence
ConTaCT: Deciding to Communicate during Time-Critical Collaborative Tasks in Unknown, Deterministic Domains
published2016 · Proceedings of the AAAI Conference on Artificial Intelligence · 32 citations
with Vaibhav Unhelkar
Proceedings of the AAAI Conference on Artificial Intelligence
Mind the Gap: a generative approach to interpretable feature selection and extraction
published2015 · Neural Information Processing Systems · 94 citations
with Been Kim, Finale Doshi-Velez
no link
On Fairness in Decision-Making under Uncertainty: Definitions, Computation, and Comparison
published2015 · Proceedings of the AAAI Conference on Artificial Intelligence · 9 citations
with Chongjie Zhang
Proceedings of the AAAI Conference on Artificial Intelligence
Scalable and Interpretable Data Representation for High-Dimensional, Complex Data
published2015 · Proceedings of the AAAI Conference on Artificial Intelligence · 18 citations
with Been Kim, Kayur Patel, Afshin Rostamizadeh
Proceedings of the AAAI Conference on Artificial Intelligence

Assembled from arXiv and OpenAlex. Duplicate records for the same paper are merged, and the published version is shown where we could identify one. Corrections welcome.