Wenbo Zhang

Irvine, California, US

Welcome! I am a fifth-year Statistics PhD candidate at University of California Irvine. I am supervised by professor Hengrui Cai. Previously, I studied Biostatistics as a master student at the University of Washington. Prior to UW, I received my BSc in Applied Mathematics from Xi’an Jiaotong-Liverpool University.

Research Interests: I have broad research interests in general machine learning. Specifically, my research interests lie in:

Post-training of Large Language Models, e.g. RLHF, RLVR, distillation, etc.
Trustworthy AI, e.g. uncertainty quantification, interpratability, efficient and robust benchmark evaluation, etc..

selected publications

For a complete list, see the publications page, or my google scholar page.

(*=equal contribution)

TMLR

Where to Intervene: Action Selection in Deep Reinforcement Learning

Wenbo Zhang , and Hengrui Cai

Transactions on Machine Learning Research, 2025

Bib PDF Code

@article{zhang2025where,
  title = {Where to Intervene: Action Selection in Deep Reinforcement Learning},
  author = {Zhang, Wenbo and Cai, Hengrui},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2025},
  url = {https://openreview.net/forum?id=D3au9XkWuy},
  note = {},
}

JRSSB

Interpretable discriminant analysis for functional data supported on random nonlinear domains with an application to Alzheimer’s disease

Eardi Lila , Wenbo Zhang , and Swati Rane Levendovszky

Journal of the Royal Statistical Society Series B: Statistical Methodology, 2024

Bib PDF

@article{lila2024interpretable,
  title = {Interpretable discriminant analysis for functional data supported on random nonlinear domains with an application to Alzheimer’s disease},
  author = {Lila, Eardi and Zhang, Wenbo and Rane Levendovszky, Swati},
  journal = {Journal of the Royal Statistical Society Series B: Statistical Methodology},
  url = {https://academic.oup.com/jrsssb/advance-article/doi/10.1093/jrsssb/qkae023/7633881},
  year = {2024},
}

ICML

Towards trustworthy explanation: On causal rationalization

Wenbo Zhang , Tong Wu , Yunlong Wang , and 2 more authors

International Conference on Machine Learning, 2023

Bib PDF Code

@article{zhang2023towards,
  title = {Towards trustworthy explanation: On causal rationalization},
  author = {Zhang, Wenbo and Wu, Tong and Wang, Yunlong and Cai, Yong and Cai, Hengrui},
  journal = {International Conference on Machine Learning},
  url = {https://proceedings.mlr.press/v202/zhang23ap.html},
  year = {2023},
}