Trustworthy AI through Knowledge and Optimization Lab
Directed by Prof. Zhe Zeng
We perform research in artificial intelligence (AI) and machine learning (ML) with focus on neurosymbolic AI. Our goal is to enable and support decision-making in the real world in the presence of probabilistic uncertainty and symbolic knowledge (graph structures, logical, arithmetic, and physical constraints, etc) to achieve trustworthy AI and aid scientific discoveries.
News
-
paperTwo papers accepted to ICML 2026: ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts and Automatic Layer Selection for Hallucination Detection 🎉
-
paperOne paper accepted to NeSy 2026: Learning Deep Generative Models under Hard Linear Equality Constraints 🎉
-
fundingWe received the DAC award. Thank you UVA RC!
-
teamWelcome Zhizhen, Heng and Xinpeng to the group 🥳
Recent Publications
All publications →-
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
Heng Zhao, Zilei Shao, Guy Van den Broeck, Zhe Zeng
International Conference on Machine Learning (ICML) , 2026
-
Automatic Layer Selection for Hallucination Detection
Xinpeng Wang, William X. Cao, Andrew Gordon Wilson, Zhe Zeng
International Conference on Machine Learning (ICML) , 2026
-
Learning Deep Generative Models under Hard Linear Equality Constraints
Ruoyan Li, Dipti Ranjan Sahu, Guy Van den Broeck, Zhe Zeng
Proceedings of Machine Learning Research (PMLR) , 2026
-
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye, Luyang Jiang, Eric Xie, Guangtao Zheng, Yunsheng Ma, Xu Cao, Dongliang Guo, Daiqing Qi, Zeyu He, Yijun Tian, Megan Coffee, Zhe Zeng, Sheng Li, Ting-Hao Kenneth Huang, Ziran Wang, James M. Rehg, Henry Kautz, Andrew Gordon Wilson, Aidong Zhang
Transactions on Machine Learning Research , 2026
Recent Talks
All talks →Invited Talk — Oct 2025
Constraining Deep Generative Models with Neurosymbolic Approach
AI/ML Seminar at UVA
Guest Lecture — Sep 2025
Neurosymbolic Learning and Reasoning for Trustworthy AI
CS6190 at UVA
Invited Talk — Aug 2024
Neurosymbolic Learning and Reasoning for Trustworthy AI
Seminar on Artificial Intelligence and Logics (SNAIL) at University of São Paulo
Invited Talk — Oct 2023
Weighted Model Integration
Probabilistic Circuits and Logic Workshop at Simons Institute, UC Berkeley
Research Sponsors