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 an Associate Professor and Samueli Fellow at UCLA, in the Computer Science Department, 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

2024

[204], and . Scaling Tractable Probabilistic Circuits: A Systems Perspective, In Proceedings of the 41th International Conference on Machine Learning (ICML), .
[203], , , and . Learning to Discretize Denoising Diffusion ODEs, In Arxiv, .
[202], , and . A Tractable Inference Perspective of Offline RL, In Arxiv, .
[201], , and . Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models, In Arxiv, .
[200], , , , and . A Circus of Circuits: Connections Between Decision Diagrams, Circuits, and Automata, In Arxiv, .
[199], and . Polynomial Semantics of Tractable Probabilistic Circuits, In Proceedings of the 40th Conference on Uncertainty in Aritifical Intelligence (UAI), .  
[198], and . Image Inpainting via Tractable Steering of Diffusion Models, In Proceedings of the Twelfth International Conference on Learning Representations (ICLR), .
[197], , , , , and . Probabilistically Rewired Message-Passing Neural Networks, In Proceedings of the Twelfth International Conference on Learning Representations (ICLR), .
[196], , , , , , , , , , , , , , , , , , , , , , , and . On the Challenges and Opportunities in Generative AI, In Arxiv, .

2023

[195], , and . A Unified Approach to Count-Based Weakly Supervised Learning, In Advances in Neural Information Processing Systems 36 (NeurIPS), .

Recent Talks