I'm a postdoctoral researcher working with Eero Simoncelli at the Flatiron Institute's Center for Computational Neuroscience. My research lies at the intersection of computer vision, machine learning, and information theory. I'm particularly interested in unsupervised representation learning, inverse problems, data compression, and generative modeling. What intrigues me most about these seemingly different problems is that they are, in fact, intimately related. For instance, even solving the "simplest" inverse problem of denoising yields powerful representations of data, state-of-the-art compression engines, and among the best generative models to date (diffusion models). I believe that investigating the relationships between these fundamental problems will ultimately deepen our understanding of intelligence and, in turn, enable us to design better artificial intelligence systems.

Previously, I received a PhD in Computer Science from the Technion—Israel Institute of Technology, where I was advised by Michael Elad and Tomer Michaeli. My doctoral research focused on designing image restoration and compression algorithms based on generative models, and on studying their theoretical limits. You can download my PhD dissertation from this link.