Shawn Im

Hello! My interest is in developing an understanding of the systems underlying the behavior of machine learning models. Not only is this understanding crucial for safe and beneficial models, but also, as models grow to understand more about the world and human values, a strong understanding of their behavior has the potential to lead to new insights of the world and ourselves. Currently, I am working on understanding how models represent their beliefs and reasoning as well as developing ways for us to better explore the shape of the model's internals.

I am a PhD student at UW-Madison working with Prof. Sharon Li. I am thankful to be supported by the NSF GRFP. Previously, I was a Machine Learning Research intern at Apple. I completed my undergraduate degrees in mathematics and computer science at MIT.