Published multiple papers on topics such as confidence calibration in vision-language-action models, guiding LLM decision-making with fairness reward models, enhancing estimates of quantile-based distributional measures using model predictions, and adaptive elicitation of latent information. Won Best Paper at ICLR 2025 workshop on Uncertainty and Hallucination in Foundation Models and the Jonathan L. Gross Prize for Academic Excellence from Columbia University's Department of Computer Science.
Research Experience
Enabling trustworthy machine learning and AI deployments, especially in important domains like medicine and education.
Education
Columbia University, Ph.D. in Machine Learning, advised by Richard Zemel, and also works closely with Hongseok Namkoong and Kathleen McKeown.
Background
Currently a 3rd year machine learning Ph.D. student at Columbia University, with research interests in uncertainty quantification, LLMs, skiing, and baseball. Also serves as a board member for the Midnight Run.