Spencer Hill

Hi there! I’m Spencer Hill, a first-year computer science PhD student at the University of Toronto and the Vector Institute, supervised by Chris Maddison and Murat Erdogdu. My research aims to understand and improve modern deep learning systems. Recently, I have been thinking about fundamental questions in pretraining, especially around tokenization and scaling laws.

Previously, I completed my MASc degree in mathematics at Queen’s University under the supervision of Fady Alajaji and Tamás Linder. There, I worked on data compression and information theory, in particular the problem of channel simulation/relative entropy coding. Further back, I hold a BASc (Engineering) degree from Queen’s University, where I studied Mathematics and Engineering.

My email is [firstname] @ cs.toronto.edu.