Furong Jia
(I also go by Flora)

Hi! I am a second-year Computer Science PhD student at Duke University, supervised by Prof. Monica Agrawal. Previously, I received my Bachelor of Science in Computer Science and Applied and Computational Mathematics from University of Southern California, where I was fortunate to work with Prof. Yan Liu, Prof. Jesse Thomason, and Prof. Maja Matarić.

Research: My research centers on developing a principled understanding of large foundation models, particularly large language models (LLMs), with the aim of enhancing their capabilities, addressing their limitations, and optimizing their deployment across diverse applications. I am broadly interested in making these AI systems reliable, interpretable, and robust by understanding how data shapes model behavior at training and inference time. My specific interests include developing methods that leverage properties of diverse data (text, time-series, multimodal) to make models adaptable to changes that arise during both training and deployment. A parallel interest is applying these approaches in clinical contexts, where robustness, generalizability, and responsible deployment are critical.

Feel free to reach out to me if you'd like to discuss research or explore potential collaboration!

Email / Github / Twitter / CV / Google Scholar