Statistical and Relational Artificial Intelligence Lab
UCLA - Computer Science Department
Engineering VI Room 368A
404 Westwood Plaza
Los Angeles, CA 90095-1596
Engineering VI Room 368A
404 Westwood Plaza
Los Angeles, CA 90095-1596
The Statistical and Relational Artificial Intelligence (StarAI) lab is directed by Prof. Guy Van den Broeck. The StarAI lab performs research on Machine Learning (Tractable Deep Generative Models, Statistical Relational Learning, Probabilistic Programming), Knowledge Representation and Reasoning (Probabilistic Inference, Probabilistic Databases), and Artificial Intelligence in general.
Recent Publications
2026 | |
| [257] | . Learning Deep Generative Models under Hard Linear Equality Constraints, In Proceedings of the 20th International Conference on Neurosymbolic Learning and Reasoning (NeSy), Proceedings of Machine Learning Research, volume 284, 2026. |
| [256] | . Interpretable Causal Discovery via Causal-Effect Constraints, In Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence (UAI), 2026. |
| [255] | . Mitigating Bias in Locally Constrained Decoding via Tractable Proposals, In Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026. |
| [254] | . ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts, In Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026. |
| [253] | . Probabilistic Programs of Thought, In Arxiv, 2026. |
| [252] | . A canonical generalization of OBDD, In Proceedings of the 29th International Conference on Theory and Applications of Satisfiability Testing (SAT), 2026. |
| [251] | . Breaking the Factorization Barrier in Diffusion Language Models, In Arxiv, 2026. |
| [250] | . ExplainFuzz: Explainable and Constraint-Conditioned Test Generation with Probabilistic Circuits, In Arxiv, 2026. |
| [249] | . GPC: Deep generative model of genetic variation data improves imputation accuracy in private populations, In ICLR Workshop on Generative AI in Genomics (Gen2): Barriers and Frontiers, 2026. |
| [248] | . Rethinking Probabilistic Circuit Parameter Learning, In Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. Oral full presentation, acceptance rate 0.5% |
