Zeeshan Patel

I am an undergraduate student at UC Berkeley studying Computer Science and Statistics. My main research focus is in generative computer vision and AI generalization for vision tasks. Currently, I am researching at Berkeley Artificial Intelligence Research (BAIR), and I am advised by PhD student Yossi Gandelsman and Professor Alexei Efros.

I am also currently interning at Apple AI/ML as a ML Engineer on the Information Intelligence team working on Foundation Models. Previosuly, I have also interned at Verkada on the Special Projects team as a ML engineer.

Email  /  Github

profile photo

I'm broadly interested in machine learning, computer vision, NLP, and AI generalization. Specifically, I'm interested in understanding how to create vision systems that can continuously generalize under distribution shifts. I'm also interested in the intersection of vision and language and how generative vision models can leverage language to interact with humans.

Test-Time Training for Image Superresolution
Zeeshan Patel*, Yossi Gandelsman
Preprint, 2023

A self-supervised approach for fine-tuning image superresolution models to adapt to new test distributions on-the-fly.

Website template from John Barron.