Yue Xing

Welcome to my homepage!

I'm an Assistant Professor at the Department of Statistics and Probability and Department of Computer Science and Engineering (courtesy) at Michigan State University.

I received my Ph.D. degree at Purdue, advised by Prof. Guang Cheng and Prof. Qifan Song. Before joining Purdue, I obtained M.Phil. degree in Risk Management Science at the Chinese University of Hong Kong, supervised by Prof. Tony Sit and Prof. Hoi Ying Wong. I got my B.Sc. degree at CUHK, major in Risk Management Science, major in Computer Science. 

Google Scholar: link

Email: xingyue1 [at] msu [dot] edu

CV: link

Research interests: Statistical theory in Large Language Models (LLM), adversarial robustness, and Trustworthy AI. High-dimensional statistics. Survival analysis.

Selected publications: [Full list]

• Pengfei He, Zitao Li, Yue Xing, Yaling Li, Jiliang Tang, Bolin Ding, Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning. arXiv

• Rajdeep Haldar, Ziyi Wang, Qifan Song, Guang Lin, Yue Xing. LLM Safety Alignment is Divergence Estimation in Disguise. arXiv

• Pengfei He, Yingqian Cui, Han Xu, Hui Liu, Makoto Yamada, Jiliang Tang, Yue Xing (2025), Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study. Stat, AI special issue. arXiv

• Jie Ren*, Yaxin Li*, Shenglai Zen, Han Xu, Lingjuan Lyu, Yue Xing, Jiliang Tang (2024), Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention. ECCV2024. arXiv

• Yingqian Cui, Pengfei He, Xianfeng Tang, Qi He, Chen Luo, Jiliang Tang, Yue Xing, A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration. AISTATS 2025. arXiv

• Yue Xing, Xiaofeng Lin, Qifan Song, Yi Xu, Belinda Zeng, Guang Cheng (2024), Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective. AISTATS2024. arXiv

• Yue Xing, Qifan Song, Guang Cheng (2021), On the Algorithmic Stability of Adversarial Training. Neurips 2021. Openreview