Junrui (Arielle) Zhang

I'm a first year PhD student in machine learning at the University of Toronto & Vector Institute supervised by Professor Nicolas Papernot.

My work focuses on working with the fundamentals of large models to benefit both AI capability and safety. I am interested in LLM unlearning, mechanistic interpretibility, training data attribution, and improving LLM's reasoning abilities.

Previously, I studied Engineering Science (Machine Intelligence) at the University of Toronto, during which I completed my 8-month internship at Huawei Technologies Canada working on robust prediction methods for self-driving cars.