About

I’m a PhD student in Computer Science at the University of Colorado Boulder (CU Boulder), and a member of the Science of Science and Computational Discovery Lab. I’m advised by Prof. Daniel Acuña. My research interests include AI safety and alignment, Natural Language Processing (NLP), and Science of Science, with an emphasis on reliable, safe, and responsible large language models for scientific work.

Broadly, I’m interested in building safer and more trustworthy language models for scientific use. My research focuses on AI safety and alignment for scientific workflows—especially how models handle uncertainty, pressure, and research integrity. I also study what LLMs internalize and output about science and scientists, and how these representations may shape scientific communication and decision-making. Recently, I’ve been developing benchmarks to test whether LLMs can recognize and avoid research misconduct, and exploring principle-driven methods to encourage more truthful, integrity-preserving behavior.

Before starting my PhD, I completed a postgraduate diploma in Quantitative Life Sciences at the Abdus Salam International Centre for Theoretical Physics (ICTP), and a Master’s in Data Science at the African Institute for Mathematical Sciences. I also earned an MS in Physics (Electronics, Electrical Engineering, and Automation) from the University of Dschang.