Sotabase

Career

· PhD candidate, Massachusetts Institute of Technology (MIT), CSAIL Interactive Robotics Group2023–
· Associate Product Manager, Google

Publications (23)

Do Feature Attribution Methods Correctly Attribute Features?
AAAI Conference on Artificial Intelligence · 2021
157
cited
IEEE P7001: A Proposed Standard on Transparency
Frontiers in Robotics and AI · 2021
94
cited
The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications
AAAI Conference on Artificial Intelligence · 2023
94
cited
Piggybacking Robots: Human-Robot Overtrust in University Dormitory Security
IEEE/ACM International Conference on Human-Robot Interaction · 2017
91
cited
Models of human preference for learning reward functions
Trans. Mach. Learn. Res. · 2022
59
cited
Machine Learning Practices Outside Big Tech: How Resource Constraints Challenge Responsible Development
AAAI/ACM Conference on AI, Ethics, and Society · 2021
50
cited
Revisiting Human-Robot Teaching and Learning Through the Lens of Human Concept Learning
IEEE/ACM International Conference on Human-Robot Interaction · 2022
23
cited
Evaluating the Interpretability of the Knowledge Compilation Map: Communicating Logical Statements Effectively
International Joint Conference on Artificial Intelligence · 2019
21
cited
Bayes-TrEx: a Bayesian Sampling Approach to Model Transparency by Example
AAAI Conference on Artificial Intelligence · 2020
20
cited
The Irrationality of Neural Rationale Models
TRUSTNLP · 2021
18
cited
RoCUS: Robot Controller Understanding via Sampling
Conference on Robot Learning · 2020
16
cited
Quality-Diversity Generative Sampling for Learning with Synthetic Data
AAAI Conference on Artificial Intelligence · 2023
8
cited
Bayes-TrEx: Model Transparency by Example
2020
5
cited
Variable Autonomy for Human-Robot Teaming (VAT)
IEEE/ACM International Conference on Human-Robot Interaction · 2023
4
cited
Bayes-Probe: Distribution-Guided Sampling for Prediction Level Sets
arXiv.org · 2020
2
cited
Human-Interactive Robot Learning: Definition, Challenges, and Recommendations
ACM Transactions on Human-Robot Interaction · 2025
2
cited
Varying How We Teach: Adding Contrast Helps Humans Learn about Robot Motions
2023
2
cited
Sampling Prediction-Matching Examples in Neural Networks: A Probabilistic Programming Approach
arXiv.org · 2020
1
cited
Aligning Robot Behaviors with Human Intents by Exposing Learned Behaviors and Resolving Misspecifications
IEEE/ACM International Conference on Human-Robot Interaction · 2023
On Applications of the Equilibrium Value Method
2014
Sotabase
Serena Booth | Researcher Profile | Sotabase | Sotabase