Zenan Li
Scholar

Zenan Li

Google Scholar ID: eu4eqTcAAAAJ
ETH Zurich
Deep learningNeuro-symbolic AINeural theorem proving
Citations & Impact
All-time
Citations
640
 
H-index
11
 
i10-index
13
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • - Paper: Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models, NeurIPS 2025
  • - Paper: A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning, NeurIPS 2025
  • - Paper: Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning, ICLR 2025
  • - Paper: Decoupling Training-Free Guided Diffusion by ADMM, CVPR 2025
  • - Paper: Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency, NeurIPS 2024
  • - Paper: Neuro-Symbolic Data Generation for Math Reasoning, NeurIPS 2024
  • - Paper: A Survey on Deep Learning for Theorem Proving, COLM 2024
  • - Paper: Neuro-symbolic Learning Yielding Logical Constraints, NeurIPS 2023
  • - Paper: Learning with Logical Constraints but without Shortcut Satisfaction, ICLR 2023
  • - Paper: Softened Symbol Grounding for Neuro-symbolic Systems, ICLR 2023
  • - Paper: Lightweight Approaches to DNN Regression Error Reduction: An Uncertainty Alignment Perspective, ICSE 2023
Research Experience
  • - Post-doc researcher at the Department of Computer Science and Technology, ETH Zürich
Education
  • - Ph.D.: Nanjing University, Advisors: Xiaoxing Ma, Jian Lü
  • - M.S.: Software Institute, Nanjing University
  • - B.S.: School of Mathematics, Southwest Jiaotong University
Background
  • - Currently a postdoctoral researcher at ETH Zürich, supervised by Zhendong Su
  • - Ph.D. from Nanjing University, advised by Xiaoxing Ma and Jian Lü
  • - Bachelor of Science from Southwest Jiaotong University, Master of Science from the Software Institute of Nanjing University
  • - Research interests include the integration of deep learning and software engineering, neuro-symbolic AI, and its applications in mathematical reasoning, theorem proving, and verified code generation