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 | |
| [243] | . Rethinking Probabilistic Circuit Parameter Learning, In Proceedings of the 29th International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. Oral spotlight presentation, acceptance rate 3% |
| [242] | . Planned Diffusion, In Proceedings of the 14th International Conference on Learning Representations (ICLR), 2026. |
| [241] | . Algorithms for Optimizing Acyclic Queries, In Proceedings of the 29th International Conference on Database Theory (ICDT), 2026. |
| [240] | . Enabling Autoregressive Models to Fill In Masked Tokens, In Findings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026. |
| [239] | . How to Marginalize in Causal Structure Learning?, In 5th Workshop on Graphs and more Complex Structures For Learning and Reasoning (GCLR), 2026. |
| [238] | . ESTroM: Element-Flow Architecture For Processing Sparse Tractable Probabilistic Models, In Proceedings of the 32nd International Symposium on High-Performance Computer Architecture (HPCA), 2026. |
2025 | |
| [237] | . Accelerating Diffusion LLMs via Adaptive Parallel Decoding, In Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. Oral spotlight presentation, acceptance rate 688/21575 = 3.1% |
| [236] | . Plug-and-Play Context Feature Reuse for Efficient Masked Generation, In Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. |
| [235] | . Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion, In Advances in Neural Information Processing Systems 38 (NeurIPS), 2025. |
| [234] | . Zero-Variance Gradients for Variational Autoencoders, In NeurIPS 2025 Workshop on Structured Probabilistic Inference & Generative Modeling, 2025. |
