Gilad Turok

Hi , I’m Gilad. I’m a Computer Science PhD student at Cornell University , supported by the NSF Graduate Research Fellowship. I am fortunate to work with Professors Volodymyr Kuleshov and Chris De Sa.

My research focuses on diffusion language models for parallel, controllable, and any-order text generation . I design principled and efficient methods for their pre-training, post-training, and inference. I’m broadly interested in probabilistic machine learning:

• Generative models: diffusion, flows, few-step generation
• Probabilistic foundations: sampling, inference, measure transport
• Applications: AI4Science and efficient ML systems

This summer I’m interning at Adobe Research, and previously I interned at Uber. Before grad school, I spent two wonderful years at the Simons Foundation’s Flatiron Institute with Bob Carpenter. Before that, I graduated from Columbia University with a BA in Applied Mathematics.