Dr. Qiang Liu

Biography

Qiang Liu is an Associate Professor at the University of Texas at Austin specializing in algorithm development with a focus on simplifying complexity and uncovering mathematical insights. His research broadly encompasses the algorithmic core of machine learning, aspiring to unlock new capabilities through mathematical understanding. His notable works include advancements in Diffusion Models, Generative Modeling, and Neural Architecture Optimization. He investigates various optimization problems, notably through his work on Dynamic Barrier Descent and Off-Policy Evaluation, contributing to the understanding of certifiable robustness properties in language models. Liu has a strong emphasis on Stein Variational Inference, employing advanced learning techniques to navigate complex probabilistic models. His commitment to research is matched by a passion for teaching, where he engages undergraduates in foundational courses such as Intro to Machine Learning and Optimization, alongside graduate-level theory and practices. His goal is to inspire and guide the next generation of researchers in applied machine learning and optimization.

Research Interests

Courses