Hi there! I'm Yonatan (Yoni) Slutzky, a direct-track Ph.D. candidate in the School of Computer Science and AI at Tel Aviv University, fortunately advised by Prof. Nadav Cohen. Previously, I graduated summa cum laude with a B.Sc. in Computer Science, Statistics, and Operations Research from Tel Aviv University. I spent Spring 2026 as a visiting researcher at the Institute for Mathematical and Statistical Innovation (IMSI) in Chicago.
My work revolves around the theoretical foundations of deep learning, with the goal of uncovering principles that can improve practice. In particular, I focus on the intersection of deep learning with sequence modeling, reinforcement learning, and control.
Other interests of mine include strength sports and pro wrestling.
Why Does Agentic Safety Fail to Generalize Across Tasks?
Yonatan Slutzky, Yotam Alexander, Tomer Slor, Yoav Nagel, Nadav Cohen
arXiv preprint arXiv:2605.06992, 2026
Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
Yotam Alexander, Yonatan Slutzky, Yuval Ran-Milo, Nadav Cohen
Conference on Neural Information Processing Systems (NeurIPS), 2025
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
Yonatan Slutzky*, Yotam Alexander*, Noam Razin, Nadav Cohen
Conference on Neural Information Processing Systems (NeurIPS), 2025
Teaching Assistant
Intro to Machine Learning 0368-3235
Spring 2025—Present
Teaching Assistant
Foundations of Deep Learning 0368-3080
Spring 2024—Present
Teaching Assistant
Workshop on Deep Learning 0368-3538
Spring 2024—Present
Teaching Assistant
Statistical Learning 0365-4063
Fall 2023
© 2025 Yonatan Slutzky. All rights reserved.
Last updated: March 2026