
1/4000s, f/1.2, ISO 100
I’m Yiwei (yee-way) Fu (foo), an incoming CS PhD student at University of Illinois Urbana-Champaign (UIUC). Previously, I had a master’s degree in machine learning at Carnegie Mellon University. Before that, I graduated from University of Michigan majoring in Honors Mathematics and Computer Science.
My research interest is in the privacy, safety, and security of machine learning, especially their connections with each other. I’m broadly interested in differential privacy, safety, and alignment of generative models with their information theoretic implications, and efficient and secure machine learning systems.
I am currently working at W. W. Grainger as an applied machine learning scientist.
Email: yiwei_fuscz AT outlook.com / fyw AT umich.edu
Research
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith
The Thirteenth International Conference on Learning Representations, 2025
[PDF]
Notes and Blogs
-
Math 669, Combinatorics of Integer Points
— Chemistry memories somehow showed up
-
Math 668, Combinatorics of $\operatorname{GL}_n \mathbb{C}$ Representation
— Let's do this
-
EECS 550, Infomation Theory
— So many noise, but I only want to hear you
-
Math 566, Algebraic Combinatorics
— cool stuff
-
Math 597, Analysis II
— Measure & Integration
-
Math 493 & 494, Honors Algebra
— Group theory, representation theory, rings
-
Math 525, Probability Theory
— No measure theory here
-
Math 389, Winter 2021 Term
— Something we did in this interesting course
-
Notes of A Mathematician's Apology, Ch.3
— A Mathematical examination of mathematics, cont'd
-
Notes of A Mathematician's Apology, Ch.2
— A Mathematical examination of mathematics, cont'd
-
Notes of A Mathematician's Apology, Ch.1
— A Mathematical examination of mathematics