Bio
Tony Bui (Research AI Software Engineer) is a computer scientist working at the intersection of natural language processing, mental health, and human-centered AI. He collaborates with Stanford’s Institute for Human-Centered AI (HAI)—in the Computational Psychology and Well-Being Lab—and with Vanderbilt University’s Human Language Analysis Beings (HLAB). He builds evaluation-driven systems that make large language models safer and more useful in clinical training and public-health research. Tony co-organizes SemEval 2026 Task 2 on predicting variation in emotional valence and arousal over time, leading dataset curation, evaluation scripts, and competition infrastructure. He is the lead engineer of TherapyTrainer, a voice-enabled simulation platform that combines retrieval-augmented generation (RAG), LLMs, and analytics to provide feedback to trainees. An active open-source contributor, he modernized the Differential Language Analysis Toolkit (DLATK) and deployed multiple behavioral-analysis pipelines. His broader interests include trustworthy and multilingual LLMs, multimodal signals (text and audio), rigorous evaluation, and equitable access to evidence-based care. Tony holds a B.S. in Computer Science from Stony Brook University and has shipped full-stack products across research labs, hospitals, and startups.