I am currently a Senior Research Scientist at Google Research.

My research explores ways to automatically evaluate and improve generative AI models and RAG systems. Recently, we have shown that RAG systems suffer from hallucinations and often fail to abstain by analyzing datasets and models through the lens of Sufficient Context. We have introduced the new SLED decoding method to improve LLM factuality. Digging deeper, we have provided a mechanistic analysis of how Transformers solve propositional logic problems. I also work on multi-modal LLMs, including a new text-to-image evaluation with Gecko, better alignment with DreamSync, and all around improvements with Imagen 3.

Prior to Google, I was a postdoc at UCSD in the CSE department, working with Kamalika Chaudhuri, Sanjoy Dasgupta, and Paul Siegel. Before this, I was a visiting Research Scientist at Facebook Reality Labs, exploring Distributed Computing and Augmented Reality. In June 2018, I received my PhD in Computer Science & Engineering from the University of Washington (UW). My advisor was Paul Beame, and I was a part of both the Theory and MISL groups. I also spent time at Microsoft Research, working with the DNA Storage and the Theory groups. I obtained my BS from the Department of Computer Science at the University of Illinois Urbana-Champaign (UIUC).

For more information, take a look at my Publications. See also the UCSD Machine Learning Blog for expository articles about some previous papers and more.