Published multiple papers, including 'PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health Organizations' (IAAI '26), 'Do Concept Bottleneck Models Obey Locality?' (TMLR '25), and more.
Research Experience
Deployed work in domains such as food sustainability and behavioral health; research projects include how to best incorporate human preferences when evaluating AI systems, designing explainability methods that complement human decision-makers, and designing mechanisms that allow for participant choice while maximizing overall welfare.
Education
PhD: Carnegie Mellon University, advised by Fei Fang; MPhil: University of Cambridge in Advanced Computer Science, worked with Mateja Jamnik; BS: University of Maryland in Computer Science and Math, worked with John Dickerson and Jordan Boyd-Graber.
Background
PhD student in the Machine Learning Department at Carnegie Mellon University, with research interests in human feedback in algorithmic decision-making, evaluation methods, explainability, and participant choice mechanisms.