Portrait of Poorva Garg, Ascent Fellow 2027
2027 ASCENT FELLOW

Poorva Garg

PhD Candidate
UCLA
Formal Methods + AI

Highlighted research

Probabilistic Programs of Thought

arXiv preprint, 2026

Biography

Poorva Garg is a final-year Ph.D. candidate in the Department of Computer Science at UCLA, co-advised by Prof. Guy Van den Broeck and Prof. Todd Millstein. Her research lies at the intersection of probabilistic artificial intelligence and programming languages, spanning probabilistic programming languages, formal methods, and large generative models. Her work centers on identifying and exploiting structure in probability distributions to design reasoning methods that are both scalable and accurate. This perspective guides her current work on AI code generation, where she treats generated code as a probabilistic program to make generation more robust and efficient. The same perspective earlier led her to develop bit-level symbolic inference algorithms for discrete-continuous probabilistic programs, work that was nominated for a Distinguished Paper Award at PLDI 2024. Her research has been supported by an Amazon Science Hub Fellowship, and she has been named a UCLA Graduate Dean’s Scholar.