Hi! I am a postdoc at Cornell, working with Emma Pierson and Jenna Wiens. I completed my Ph.D. in the Clinical and Applied Machine Learning group at MIT, where I was lucky to be advised by John Guttag. Before, I was at MIT for undergrad, where I majored in computer science with a concentration in South Asian studies.
I work on data-centric machine learning. I often think about gaps between the data we collect and the data machine learning systems expect and develop methods to bridge the divide, inspired by applications in healthcare. Some areas I work on:
Measuring human behavior
I develop methods to measure how human behavior shapes the data used to train ML systems in healthcare, allowing us to better measure underdiagnosis (NWH 2024), disparities in care (CHIL 2025), and effects of financial incentives.
Post-training
How can we better adapt and evaluate trained machine learning models? My work focuses on methods for test-time intervention—such as test-time augmentation (ICCV 2021, CVPR 2025)—and on new methods for model evaluation (CHI 2023, under review).
Health equity
I study the intersection of machine learning and health equity, including the use of large language models to promote equity (NEJM AI 2025), guidelines for evaluating algorithmic fairness (MLHC 2023), and applications in women's health (NWH 2024, SR 2023).