UCLA StarAI Lab

Statistical and Relational Artificial Intelligence Lab

UCLA - Computer Science Department
Engineering VI Room 368A
404 Westwood Plaza
Los Angeles, CA 90095-1596

https://github.com/UCLA-StarAI
guyvdb@cs.ucla.edu
guy@sigmoid.social
@guyvdb

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

2025
[238]	Daniel Israel, Guy Van den Broeck and Aditya Grover. Accelerating Diffusion LLMs via Adaptive Parallel Decoding, 2025. Oral spotlight presentation, acceptance rate 688/21575 = 3.1%
[237]	Zilei Shao, Anji Liu and Guy Van den Broeck. Zero-Variance Gradients for Variational Autoencoders, In NeurIPS 2025 Workshop on Structured Probabilistic Inference & Generative Modeling, 2025.
[236]	Zheng Luo, Wim Van den Broeck, Guy Van den Broeck and Yisu Remy Wang. Algorithms for Optimizing Acyclic Queries, In Arxiv, 2025.
[235]	Ryan Tjoa, Poorva Garg, Harrison Goldstein, Todd Millstein, Benjamin C. Pierce and Guy Van den Broeck. Tuning Random Generators: Property-Based Testing as Probabilistic Programming, In Proc. ACM Program. Lang. (OOPSLA), ACM, 2025.
[234]	Poorva Garg, Benjie Wang, Oliver Broadrick, Guy Van den Broeck and Todd Millstein. Bitblasting for Constrained Decorrelation in Tractable Image Modeling, In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), 2025.
[233]	Honghua Zhang, Meihua Dang, Benjie Wang, Stefano Ermon, Nanyun Peng and Guy Van den Broeck. Scaling Probabilistic Circuits via Monarch Matrices, In Proceedings of the 42th International Conference on Machine Learning (ICML), 2025.
[232]	Gwen Yidou-Weng, Benjie Wang and Guy Van den Broeck. TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation, In Proceedings of the 42th International Conference on Machine Learning (ICML), 2025.
[231]	Xuejie Liu, Anji Liu, Yitao Liang and Guy Van den Broeck. Plug-and-Play Context Feature Reuse for Efficient Masked Generation, In Arxiv, 2025.
[230]	Anji Liu and Guy Van den Broeck. Rethinking Probabilistic Circuit Parameter Learning, In Arxiv, 2025.
[229]	Anji Liu, Xuejie Liu, Dayuan Zhao, Mathias Niepert, Yitao Liang and Guy Van den Broeck. Tractable Transformers for Flexible Conditional Generation, In Proceedings of the 42th International Conference on Machine Learning (ICML), 2025.