Published multiple papers in PNAS, including 'Using LLMs to categorize strategic situations and decipher motivations behind human behaviors' (2025) and 'A Turing test of whether AI chatbots are behaviorally similar to humans' (2024)
Led/co-developed the open Behavioral Foundation Models (Be.FM)
Research featured in UMich News, Stanford News, and other media outlets
Published 'MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows' at NAACL 2025
Co-authored a perspective paper on AI Behavioral Science
Co-launched a new research topic on AI Behavioral Science in Frontiers in AI journal