About me
I am an undergraduate student in the Department of Probability and Statistics, School of Mathematical Sciences, Peking University, pursuing a B.S. in Statistics (expected 2027).
I am currently a research intern at George Mason University, advised by Prof. Ziyu Yao, where I work on mechanistic interpretability for planning-related world modelling in agents. I also work with Prof. Liangming Pan in the PKU Interpretable Large Language model And Reasoning (PILLAR) Group on mechanistic data attribution and training-data interventions for large language models.
My research interests include large language models, mechanistic interpretability, training data attribution, and alignment. Broadly, I am interested in understanding how training data gives rise to internal mechanisms and model behaviors, and how such understanding can enable targeted interventions and more reliable AI systems.
Recent work includes Mechanistic Data Attribution (MDA), accepted as an ICML 2026 Oral (Top 0.7%), and From Reweighting to Rewriting, an arXiv preprint on turning influential training examples into effective behavioral interventions.
I am applying to PhD programs for Fall 2027. Please feel free to reach out at luoyuzzhang [at] stu [dot] pku [dot] edu [dot] cn.