I am a Ph.D. student in Computer Science at Stanford. I'm fortunate to be advised by Chris Potts. I'm affiliated with the Stanford NLP Group and Stanford AI Lab.

I work on algorithms for building better small language models and deriving more value per parameter. This spans two main areas:

• Distillation - What makes distillation algorithms effective, and how they interact with reasoning, RL, and test-time compute allocation.
• Parametric knowledge - How models encode, update, and use world knowledge, and what inductive biases work better with limited capacity.

Before Stanford I worked as an engineer at Meta. I completed my B.Sc. and M.Sc. in Computer Science at Ben-Gurion University. My master's thesis focused on evaluating tokenization algorithms in LLMs (1, 2, 3, 4), and I've also worked on information retrieval (1, 2).

I’m always excited to collaborate or exchange ideas. Feel free to reach out!