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 (recent) PhD graduate from University of Waterloo. During the flash ~3.5 years at UWaterloo, I was lucky enough to be supervised by Professor Jimmy Lin and to collaborate closely with Professor Ming Li. Before coming to Canada, I spent four years at Rensselaer Polytechnic Institute and did research at Blender, supervised by Professor Heng Ji. My research area focuses on interpretability and generalizability for machine learning.
On a high level, I’m mainly interested in understanding human learning and improving machine learning. My deep belief in the connection between compression and learning in general draws my interest towards the information theoretic approaches. Besides machine learning, I also love researching about food science and neuroscience.
In addition to research, I created AFAIK.io, a map of human knowledge with @Quinn.
Selected Publications
- ACL2023What the DAAM: Interpreting Stable Diffusion Using Cross AttentionIn Proceedings of Association for Computational Linguistics (ACL), Best Paper Award, 2023