About Me

I am currently a postdoctoral researcher in the Department of Computer Science and Technology at ETH Zürich, under the supervision of Zhendong Su. I obtained my Ph.D. from Nanjing University, where I was advised by Xiaoxing Ma and Jian Lü. Prior to my doctoral studies, I received a Bachelor of Science degree from the School of Mathematics at Southwest Jiaotong University and a Master of Science degree from the Software Institute of Nanjing University.

Address: CNB H 105, Universitatstrasse 6, 8092 Zürich
Email: zenan.li@inf.ethz.ch

Research Interests

Before the large language model (LLM) era, my research mainly focused on the integration of deep learning and software engineering, particularly in enhancing quality assurance for deep learning models and advancing software engineering automation through deep learning techniques. Additionally, I was deeply engaged in mathematical optimization, including developing fast algorithms and theoretical analysis for minimax and bilevel optimization in large-scale machine learning tasks.

With the emergence of the LLM, my research interests have switched to neuro-symbolic AI. Alongside exploring the theoretical foundations of neuro-symbolic learning, I am especially interested in its practical applications, such as leveraging LLMs for mathematical reasoning, theorem proving, and verified code generation.

Education & Intern

Post-doc Researcher ETH Zürich, Switzerland Supervisor: Prof. Zhendong Su

Sep 2025 - Present

Research Intern for Systems Research Group Microsoft Research Asia, Beijing, China Mentor: Dr. Fan Yang

July 2023 - Dec 2024

Ph.D. in Computer Science Nanjing University, Nanjing, China Advisors: Prof. Xiaoxing Ma and Prof. Jian Lü

Sep 2020 - June 2025

M.Sc. in Software Engineering Nanjing University, Nanjing, China Advisors: Prof. Xiaoxing Ma

Sep 2017 - June 2020

B.Sc. in Mathematics and Applied Mathematics Southwest Jiaotong University, Chengdu, China Advisor: Prof. Chengjing Wang

Sep 2013 - June 2017

Selected Publications

Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning
Zenan Li*, Zhaoyu Li*, Wen Tang, Xian Zhang, Yuan Yao, Xujie Si, Fan Yang, Kaiyu Yang, Xiaoxing Ma
International Conference on Learning Representations (ICLR), 2025

Decoupling Training-Free Guided Diffusion by ADMM
Youyuan Zhang, Zehua Liu, Zenan Li, Zhaoyu Li, James J Clark, Xujie Si
Computer Vision and Pattern Recognition Conference (CVPR), 2025

Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
Zenan Li*, Yifan Wu*, Zhaoyu Li, Xinming Wei, Xian Zhang, Fan Yang, and Xiaoxing Ma
Advances in Neural Information Processing Systems (NeurIPS), 2024

Neuro-Symbolic Data Generation for Math Reasoning
Zenan Li*, Zhi Zhou*, Yuan Yao, Xian Zhang, Yu-Feng Li, Chun Cao, Fan Yang, and Xiaoxing Ma
Advances in Neural Information Processing Systems (NeurIPS), 2024

A Survey on Deep Learning for Theorem Proving
Zhaoyu Li, Jialiang Sun, Logan Murphy, Qidong Su, Zenan Li, Xian Zhang, Kaiyu Yang, and Xujie Si
Conference on Language Modeling (COLM), 2024

Neuro-symbolic Learning Yielding Logical Constraints
Zenan Li, Yunpeng Huang, Zhaoyu Li, Yuan Yao, Jingwei Xu, Taolue Chen, Xiaoxing Ma, Jian Lü
Advances in Neural Information Processing Systems (NeurIPS), 2023

Learning with Logical Constraints but without Shortcut Satisfaction
Zenan Li, Zehua Liu, Yuan Yao, Jingwei Xu, Taolue Chen, Xiaoxing Ma, and Jian Lü
International Conference on Learning Representations (ICLR), 2023

Softened Symbol Grounding for Neuro-symbolic Systems
Zenan Li, Yuan Yao, Taolue Chen, Jingwei Xu, Chun Cao, Xiaoxing Ma, and Jian Lü
International Conference on Learning Representations (ICLR), 2023

Lightweight Approaches to DNN Regression Error Reduction: An Uncertainty Alignment Perspective
Zenan Li, Maorun Zhang, Jingwei Xu, Yuan Yao, Chun Cao, Taolue Chen, Xiaoxing Ma, and Jian Lü
International Conference on Software Engineering (ICSE), 2023

Fair Representation Learning: An Alternative to Mutual Information
Ji Liu, Zenan Li, Yuan Yao, Feng Xu, Xiaoxing Ma, Miao Xu, and Hanghang Tong
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022

Towards effective metamorphic testing by algorithm stability for linear classification programs
Yingzhuo Yang, Zenan Li, Huiyan Wang, Chang Xu, and Xiaoxing Ma
Journal of Systems and Software (JSS), 2021

Predicted robustness as qos for deep neural network models
Yuehuan Wang, Zenan Li, Jingwei Xu, Ping Yu, Taolue Chen, and Xiaoxing Ma
Journal of Computer Science and Technology (JCST), 2020

Operational Calibration: Debugging Confidence Errors for DNNs in the Field
Zenan Li, Xiaoxing Ma, Chang Xu, Jingwei Xu, Chun Cao, and Jian Lü
ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2020

Boosting Operational DNN Testing Efficiency Through Conditioning
Zenan Li, Xiaoxing Ma, Chang Xu, Chun Cao, Jingwei Xu, and Jian Lü
ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2019

Structural Coverage Criteria for Neural Networks Could Be Misleading
Zenan Li, Xiaoxing Ma, Chang Xu, and Chun Cao
International Conference on Software Engineering, New Ideas and Emerging Results track (ICSE-NIER), 2019