Works as a research assistant with the INVITE institute at UIUC. Frequently collaborates with the Torr Vision Group at the University of Oxford. Completed a research internship with the Neurocompositional AI team in the Deep Learning Group at Microsoft Research in Summer 2025.
Education
PhD candidate at the Siebel School of Computing and Data Science, UIUC, co-advised by Professors ChengXiang Zhai and Julia Hockenmaier.
Background
CS PhD candidate at UIUC. Research vision is to help build the foundations of a cognitive science of AI, studying how foundation models like LLMs learn, represent, and process information. Focuses on interpreting and controlling the features learned and leveraged by these models, and applying such knowledge/methods to predict and improve models' generalization to novel contexts. Current research intersects primarily with NLP, (mechanistic) interpretability, cognitive science, OOD generalization, and causal machine learning; also has ongoing collaborations in synthetic data, multimodal representation learning, computational social science, and AI for education.