Kevin Farhat

What I'm Working On

I helped develop FlexOLMo, and now apply it in federated learning setups to train on privacy-sensitive cancer data across institutions as part of the Cancer AI Alliance (CAIA).

Previously, I worked at TrueMedia with Oren Etzioni, developing deepfake detection systems to safeguard the 2024 U.S. election.

I earned my BS/MS in Computer Science at the University of Washington, where I worked with Akari Asai in the H2Lab under Hannaneh Hajishirzi.

Current focus: Distributed LLM architectures Privacy-preserving training Cancer + health AI