Minghui Liu

Hi, I’m Minghui Liu!

I am a fourth-year Ph.D. student in Computer Science at the University of Maryland, College Park, where I am fortunate to be advised by Prof. Furong Huang. I am also a member of UMIACS, working on advancing the capabilities and efficiency of large language models (LLMs). Prior to starting my Ph.D., I worked as a software engineer and earned my bachelor’s degree from Trinity College in Hartford, Connecticut.

My research focuses on improving the reasoning abilities of language models and enhancing their efficiency, especially in the context of smaller LLMs that can run on personal devices. I am particularly interested in strategies such as model compression, curriculum learning, and fine-tuning techniques that make powerful language models more accessible. I believe that artificial intelligence should be democratized — usable by everyone regardless of access to large-scale computational resources.