I currently work at Amazon as an applied scientist. Before that, I received my Ph.D. degree at MIT Department of Electrical Engineering and Computer Science (EECS), advised by Prof. Julie Shah, from which I also received my Master of Science degree in 2019. Even before that, I received my Bachelor of Science in Engineering degree from Duke University, with double major in Computer Sciene and Electrical & Computer Engineering. I worked with Prof. George Konidaris and Prof. Kris Hauser on my undergraduate research on robotics.
My research is broadly on trustworthy and responsible machine learning. Specifically, I seek answers to questions such as: How to ensure that a black-box model is working correctly? How to develop a holistic understanding of both the intended and, more importantly, unintended model behaviors? What are the limits of human understanding into such complex reasoning processes? To this end, I develop models, algorithms and evaluations in interpretable machine learning for diverse domains including computer vision (CV), natural language processing (NLP) and robotics. In addition, I also explore the interplay between interpretability and other areas of responsible ML, such as fairness and robustness.[Email: firstname.lastname@example.org] [CV (PDF)] [Google Scholar] [YouTube (paper summary videos)]
* Equal Contribution ★ Recent Highlight Journal Conference Workshop Preprint Other