Guy Van den Broeck

The Pitfalls of KV Cache Compression ACL 2026 Enabling Autoregressive Models to Fill In Masked Tokens EACL 2026 Learning to Discretize Denoising Diffusion ODEs ICLR 2025 Discrete Copula Diffusion ICLR 2025 Controllable Generation via Locally Constrained Resampling ICLR 2025 Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models AISTATS 2025 Restructuring Tractable Probabilistic Circuits AISTATS 2025 Scaling Probabilistic Circuits via Monarch Matrices ICML 2025 TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation ICML 2025 Adversarial Tokenization ACL 2025 The Limits of Tractable Marginalization ICML 2025 On the Relationship Between Monotone and Squared Probabilistic Circuits AAAI 2025 Tractable Transformers for Flexible Conditional Generation ICML 2025 Probabilistically Rewired Message-Passing Neural Networks ICLR 2024 Image Inpainting via Tractable Steering of Diffusion Models ICLR 2024 A Tractable Inference Perspective of Offline RL NIPS 2024 Adaptable Logical Control for Large Language Models NIPS 2024 A Compositional Atlas for Algebraic Circuits NIPS 2024 Scaling Tractable Probabilistic Circuits: A Systems Perspective ICML 2024 Polynomial Semantics of Tractable Probabilistic Circuits UAI 2024 Where is the signal in tokenization space? EMNLP 2024 A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints NIPS 2023 SIMPLE: A Gradient Estimator for k-Subset Sampling ICLR 2023 Scaling integer arithmetic in probabilistic programs UAI 2023 Mixtures of All Trees AISTATS 2023 Collapsed Inference for Bayesian Deep Learning NIPS 2023 On the Paradox of Learning to Reason from Data IJCAI 2023 Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic Circuits ICML 2023 Scaling Up Probabilistic Circuits by Latent Variable Distillation ICLR 2023 A Unified Approach to Count-Based Weakly Supervised Learning NIPS 2023 Out-of-Distribution Generalization by Neural-Symbolic Joint Training AAAI 2023 Certifying Fairness of Probabilistic Circuits AAAI 2023 Tractable Control for Autoregressive Language Generation ICML 2023 Semantic Strengthening of Neuro-Symbolic Learning AISTATS 2023 Neuro-symbolic entropy regularization UAI 2022 PYLON: A PyTorch Framework for Learning with Constraints AAAI 2022 Lossless Compression with Probabilistic Circuits ICLR 2022 Solving Marginal MAP Exactly by Probabilistic Circuit Transformations AISTATS 2022 Semantic Probabilistic Layers for Neuro-Symbolic Learning NIPS 2022 Sparse Probabilistic Circuits via Pruning and Growing NIPS 2022 Probabilistic Sufficient Explanations IJCAI 2021 Tractable Regularization of Probabilistic Circuits NIPS 2021 A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference NIPS 2021 On the Tractability of SHAP Explanations AAAI 2021 Group Fairness by Probabilistic Modeling with Latent Fair Decisions AAAI 2021 Juice: A Julia Package for Logic and Probabilistic Circuits AAAI 2021 Probabilistic Generating Circuits ICML 2021 Tractable computation of expected kernels UAI 2021 Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns AAAI 2020 SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning CORL 2020 Counterexample-Guided Learning of Monotonic Neural Networks NIPS 2020 Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations NIPS 2020 Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits ICML 2020 Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing ICML 2020 Efficient Search-Based Weighted Model Integration UAI 2019 On Tractable Computation of Expected Predictions NIPS 2019 What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features IJCAI 2019 On Constrained Open-World Probabilistic Databases IJCAI 2019 Learning Logistic Circuits AAAI 2019 Smoothing Structured Decomposable Circuits NIPS 2019 Towards Hardware-Aware Tractable Learning of Probabilistic Models NIPS 2019 Generating and Sampling Orbits for Lifted Probabilistic Inference UAI 2019 Approximate Knowledge Compilation by Online Collapsed Importance Sampling NIPS 2018 On Robust Trimming of Bayesian Network Classifiers IJCAI 2018 Open-World Probabilistic Databases: An Abridged Report IJCAI 2017 Optimal Feature Selection for Decision Robustness in Bayesian Networks IJCAI 2017 New Liftable Classes for First-Order Probabilistic Inference NIPS 2016 Hashing-Based Approximate Probabilistic Inference in Hybrid Domains: An Abridged Report IJCAI 2016 First-Order Model Counting in a Nutshell IJCAI 2016 Anytime Inference in Probabilistic Logic Programs with Tp-Compilation IJCAI 2015 Inducing Probabilistic Relational Rules from Probabilistic Examples IJCAI 2015 Probabilistic Inference in Hybrid Domains by Weighted Model Integration IJCAI 2015 Tractable Learning for Structured Probability Spaces: A Case Study in Learning Preference Distributions IJCAI 2015 Tractable Learning for Complex Probability Queries NIPS 2015 Completeness Results for Lifted Variable Elimination AISTATS 2013 On the Complexity and Approximation of Binary Evidence in Lifted Inference NIPS 2013