Hi! I am an Empire AI Postdoctoral Fellow in the Computer Science Department at Cornell University, hosted by Yoav Artzi. I completed my Ph.D. in the Computer Science Department at the Technion under the joint supervision of Haggai Maron and Ran El-Yaniv. My research aims to make LLMs safer by detecting their misbehaviors, such as hallucinations, using structure-aware deep learning models that learn directly from their internals. I am also interested in weight-space learning, where neural networks process other neural networks. I have also worked on Geometric Deep Learning, leveraging data symmetries to build better models, with applications to Graph Neural Networks.

Previously (Summer 2022), I was a research scientist intern at Google-Verily working with Michael Elad on video analysis. In the summer of 2025, I was a research scientist intern at Meta.

Mail Scholar Github Twitter LinkedIn CV (updated Aug. 2026)