People must be easily able to specify, model, inspect, and revise robot and AI behaviors.
I design methods and tools to enable these interactions.
Trial-and-error reward design is unsanctioned, but the implications of this widespread practice have
not been studied. We conduct empirical computational and user study experiments, and we find that
trial and error leads to the design of reward functions which are overfit and otherwise misdesigned.
Published at AAAI 2023.
Project Webpage
Video:
Reward Design Perils
Looking at expressive examples can help us better understand neural network behaviors and design
better models. Bayes-TrEx is a tool to find these expressive examples. Published at AAAI 2021.
Project Webpage
In this work, we adapt a Bayes-TrEx-like framework for the task of sampling representative robot
behaviors. Led by Yilun Zhou; published at CoRL (Conference on Robot Learning) 2021.
Project Webpage (with video), Paper, Code
We look at how cognitive theories of human concept learning should inform human-robot interaction
interfaces, especially for teaching and learning tasks. In collaboation with Sana Sharma and Elena
Glassman (Harvard). Published at HRI 2022.
Website, Paper
We interviewed industry practitioners from startups, government, and non-tech companies about their
use and integration of machine learning in developing products. We analyze these interviews with
thematic analysis. Collaboration with Aspen Hopkins. Published at AIES 2021.
Paper, Poster, Slides
We design a principled evaluation mechanism for assessing feature attribution methods, and contribute
to the growing body of literature suggesting these methods cannot be trusted in the wild. Led by
Yilun Zhou, in collaboration with Marco Ribeiro (MSR). Published at AAAI 2022.
Arxiv Paper
How should we best present logical sentences to a human? Published at IJCAI 2019.
Project Webpage
My award-winning undergraduate senior thesis, a project which set out to answer the question of
whether we place too much trust in robotic systems, specifically in the physical security domain.
Published at HRI 2017.
Project Webpage
Video:
Piggybacking Robots
In 2021-2022, I served as President and in 2020-2021 as Vice President of MIT's Science Policy Initiative. I advocate for using science to inform policy, and for using policy to make science just and equitable. Pictured above with colleague Willie Boag. Not an endorsement for Senator Alexander.
I'm a strong advocate for the inclusion of women and underrepresented minorities in science. In 2019, I served as co-president of MIT's GW6: Graduate Women of Course 6. Pictured above: students from an introductory CS class I taught in Puebla, Mexico.