I am a first-year PhD student at MIT CSAIL, advised by
Dylan Hadfield-Menell.
My research interests center on aligning AI systems — such as reinforcement learning systems
and large language models — with human goals. I am also interested in the theoretical
foundations of alignment and the intersection of machine learning and causality.
Previously, I obtained my bachelor's degree at Johns Hopkins, where I worked with Professor
Rene Vidal on the theory of deep learning.
During undergrad, I also worked with Dyno Therapeutics and NASA on biological
sequence design using machine learning, combinatorial optimization, and quantum computing.
See my Google Scholar for an up-to-date list of publications.
Outside of work, I enjoy playing piano, backpacking, salsa dancing, and philosophy.
Send me an email at stew@csail.mit.edu if you want to talk :)