Zhiying (Gin) Jiang
"If the human brain were so simple that we could understand it, we would be so simple that we couldn't."

Hi, I’m Gin, a researcher with a passion for understanding and improving both machine learning and human learning.
I’m the co-founder of AFAIK.io (NextAI 2024 cohort). AFAIK is a personalized learning platform that aims at addressing inequalities in access to higher education. Our platform enables anyone to systematically learn anything in-depth at their own level without concerns about hallucinations or misinformation.
Before founding AFAIK, I earned my PhD from the University of Waterloo, where I completed my degree in about 3.5 years under the mentorship of Professor Jimmy Lin and in collaboration with Professor Ming Li. Prior to that, I spent four years at Rensselaer Polytechnic Institute, conducting research at Blender under the guidance of Professor Heng Ji.
My research focuses on the interpretability and generalizability of machine learning models, with a strong interest in the intersection of information theory and learning. I’m deeply inspired by the idea that compression lies at the heart of both human and machine learning, guiding my exploration of fundamental, theory-driven approaches.
Beyond machine learning, I love neuroscience, physics, and food science.
Selected Publications
- ACL2023What the DAAM: Interpreting Stable Diffusion Using Cross AttentionIn Proceedings of Association for Computational Linguistics (ACL), Best Paper Award, 2023