Lunjia Hu

Hi! I’m an Assistant Professor in the Khoury College of Computer Sciences at Northeastern University. I’m a member of the Northeastern Theory Group.

My research spans many areas of theoretical computer science with a focus on the foundations of trustworthy AI. Topics include:

• uncertainty quantification, calibration, LLM hallucination
• algorithmic fair prediction and decision making
• learning theory (e.g. sample complexity characterizations)
• approximation and online algorithms
• robust and interpretable machine learning
• other (pseudorandomness, computational economics, social networks)

Before joining Northeastern, I was a Postdoctoral Fellow at Harvard University’s Center for Research on Computation and Society (CRCS), where I had the pleasure of working with Cynthia Dwork, Salil Vadhan, Han Shao, and many others. I received my Ph.D. in Computer Science from Stanford University, where I was fortunate to be co-advised by Moses Charikar and Omer Reingold. Prior to Stanford, I completed my undergraduate studies in the Yao Class at Tsinghua University, receiving a B.Eng. in Computer Science and a B.S. in Mathematics.

During my PhD years, I spent two wonderful summers (2021 and 2022) interning at Apple working with Vitaly Feldman, Kunal Talwar, Parikshit Gopalan, and Preetum Nakkiran.

I’m looking for students to join the Northeastern CS PhD program in Fall 2026. If you’re interested in doing fun research with me, apply to the program and mention my name in your application. Also feel free to email me if you’re interested in my work.

I’m proud to have worked with these rising junior researchers:
Charlotte Peale, Judy Hanwen Shen, Yifan Wu, Chutong Yang

I’m teaching a theory topics course in Fall 2025: From Convex Analysis to Learning, Prediction, and Elicitation (CS 7880)