A Ph.D. student at Michigan State University will pursue research in preventing unintended consequences of artificial intelligence, thanks to an IBM Ph.D. Fellowship Award.

Yihua Zhang is one of 24 scholars around the world to receive the 2024 Fellowship prize. Zhang is a Ph.D. candidate in the Optimization and Trustworthy Machine Learning Group in the Department of Computer Science and Engineering. Zhang’s Ph.D. advisor is CSE Assistant Professor Sijia Liu.

"We must take transformative AI seriously and plan ahead,” Zhang said. “The key challenge is ensuring AI remains aligned with human values. My goal is to develop AI that is not only powerful but also trustworthy, rule-following, and ethically aligned as it evolves,” Zhang added.

Zhang’s research focuses on developing secure, safe, and ethical large language models (LLMs) and diffusion models. His work in advancing theoretical underpinnings and real-world applications has been featured at top-tier AI conferences.