Xiaoyang Nick Hu

I am a research assistant at the Oh Lab at Brown University. I received a B.S. in math, computer science, and cognitive science from the University of Michigan.

Feel free to reach out if you'd like to collaborate or chat.

Email / Google Scholar / GitHub / Twitter
Xiaoyang Nick Hu

Research

I am fascinated by both natural and artificial intelligence—their shared principles and points of divergence. My research is driven by questions about 1) the representation of abstract concepts, 2) the mechanisms underlying controlled processing, and 3) their interplay.

Sparse Feature Coactivation Reveals Composable Semantic Modules in Large Language Models
R. Deng*, X. Hu*, M. Gilbert, S. Storks, A. Taxali, M. Angstadt, C. Sripada, J. Chai
Preprint, 2025
Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm
X. Hu, R. L. Lewis
Findings of the Association for Computational Linguistics, 2025
[code] [video]
In-Context Analogical Reasoning with Pre-Trained Language Models
X. Hu*, S. Storks*, R. L. Lewis, J. Chai
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, 2023
[code]

Miscellaneous

In my free time, I like watching ⚽️ and playing 🎾. I am a fan of Real Madrid and Rafael Nadal. I am also a dad. This is the mother of my child.

Adapted from Jon Barron's website with the help of Claude.