Dang Nguyen

Hi, I’m a CS Ph.D. candidate at UCLA under the supervision of Professor Baharan Mirzasoleiman. My research focuses on data-centric methods for building efficient and reliable AI agents. I study how to improve the training of large language and vision-language models through synthetic data generation and data selection, particularly when high-quality data is limited. More recently, I have been exploring how to enable models to reason, plan, and act effectively through reinforcement learning, with a focus on agent planning, orchestration, and safe tool use. Ultimately, I aim to develop agents that can learn from data and reliably make decisions and execute complex tasks over long horizons.

Before joining UCLA, I was an AI Resident at VinAI (now Qualcomm AI). Prior to that, I received my BS degree, summa cum laude, from Toyo University. Going further back in time, I was a graduate of High School for Gifted Students (Hanoi University of Science) and a Maths Olympian (IMO 2015 Silver).