Guy Van den Broeck

UCLA - Computer Science Department
Engineering VI Room 368A
404 Westwood Plaza
Los Angeles, CA 90095-1596
Pronounce my name
guyvdb@cs.ucla.edu
guy@sigmoid.social
@guyvdb

I am a Professor of Computer Science and Samueli Fellow at UCLA, where I direct the Statistical and Relational Artificial Intelligence (StarAI) lab. My research interests are in 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

[217], , , , , , and . Enhancing and Evaluating Probabilistic Circuits for High-Resolution Lossless Image Compression, In Proceedings of the Data Compression Conference (DCC), .
[216] and . On the Relationship between Monotone and Squared Probabilistic Circuits, In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence, .
[215], , , , and . Scaling Up Probabilistic Circuits via Monarch Matrices, In AAAI'25 workshop on CoLoRAI - Connecting Low-Rank Representations in AI, .
[214], , and . Restructuring Tractable Probabilistic Circuits, In AAAI'25 workshop on CoLoRAI - Connecting Low-Rank Representations in AI, .

2024

[213], , , and . Adaptable Logical Control for Large Language Models, In Advances in Neural Information Processing Systems 37 (NeurIPS), .
[212], , and . A Tractable Inference Perspective of Offline RL, In Advances in Neural Information Processing Systems 37 (NeurIPS), .
[211], , and . A Compositional Atlas for Algebraic Circuits, In Advances in Neural Information Processing Systems 37 (NeurIPS), .
[210], , and . Discrete Copula Diffusion, In Arxiv, .
[209], , , and . Where is the signal in tokenization space?, In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), . Oral full presentation, acceptance rate 198/6105 = 3.2%
[208], , , and . Probabilistic Circuits for Cumulative Distribution Functions, In Proceedings of the UAI Workshop on Tractable Probabilistic Modeling (TPM), .

Recent Talks