Software Projects
pyjuice
A Python package for scalable training and inference with Probabilistic Circuits. The current Python flagship of the Juice library family, with GPU-accelerated training and large-scale modeling.
Code
Alea.jl
A probabilistic programming system in Julia, the successor to Dice. Supports discrete-continuous programs via bit blasting (HyBit) and parameter learning (Loaded Dice).
CodeProbabilisticCircuits.jl
A Julia package that offers efficient routines to construct, compile, learn, and reason with Probabilistic Circuits. Part of the Juice library.
CodeLogicCircuits.jl
A Julia package for constructing, compiling, and reasoning with Logic Circuits. Tractable logical reasoning support layer used by ProbabilisticCircuits.jl.
Code
Tractable Circuit Zoo
An interactive reference for tractable circuit and knowledge compilation languages. Visualizes succinctness relationships between circuit families, the queries they support, and the transforms between them.
VisitCtrl-G
Logically-constrained LLM inference. Combines any production-ready LLM with a Hidden Markov Model so outputs adhere to logical constraints expressed as deterministic finite automata, supporting infilling, keyphrase inclusion, length control, detoxification, and rhymes.
CodeSIMPLE
A gradient estimator for k-subset sampling. Drop-in replacement for biased reinforce-style estimators with substantially lower variance.
CodeCoDD
Coupled Discrete Diffusion. Adds a tractable probabilistic inference layer to one-step parallel diffusion language models, closing the misspecification gap from independence assumptions.
CodeTracformer
Tractable Transformers. A transformer architecture for flexible conditional generation that supports exact inference over arbitrary subsets of tokens.
CodeCopula-Diffusion
Discrete Copula Diffusion. Supplements discrete diffusion language models with a copula model to recover dependency information across denoising steps, enabling fast few-step generation.
CodeRecent Papers with Code
2025 | |
| [246] | . 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% |
| [245] | . Tuning Random Generators: Property-Based Testing as Probabilistic Programming, In Proc. ACM Program. Lang. (OOPSLA), ACM, 2025. |
| [244] | . Adversarial Tokenization, In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025. |
2024 | |
| [243] | . Adaptable Logical Control for Large Language Models, In Advances in Neural Information Processing Systems 37 (NeurIPS), 2024. |
| [242] | . Where is the signal in tokenization space?, In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024. Oral full presentation, acceptance rate 198/6105 = 3.2% |
| [241] | . Bit Blasting Probabilistic Programs, In Proc. ACM Program. Lang. (PLDI), Association for Computing Machinery, 2024. |
2023 | |
| [240] | . Collapsed Inference for Bayesian Deep Learning, In Advances in Neural Information Processing Systems 36 (NeurIPS), 2023. |
| [239] | . On the Paradox of Learning to Reason from Data, In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI), 2023. |
| [238] | . Mixtures of All Trees, In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. |
| [237] | . Scaling Up Probabilistic Circuits by Latent Variable Distillation, In Proceedings of the International Conference on Learning Representations (ICLR), 2023. Oral full presentation, acceptance rate 90/4849 = 1.8% |
| [236] | . SIMPLE: A Gradient Estimator for k-subset sampling, In Proceedings of the International Conference on Learning Representations (ICLR), 2023. |
| [235] | . Semantic Strengthening of Neuro-Symbolic Learning, In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. |
| [234] | . Out-of-Distribution Generalization by Neural-Symbolic Joint Training, In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023. |
| [233] | . Certifying Fairness of Probabilistic Circuits, In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023. |
2022 | |
| [232] | . Sparse Probabilistic Circuits via Pruning and Growing, In Advances in Neural Information Processing Systems 35 (NeurIPS), 2022. Oral full presentation, acceptance rate 201/10411 = 1.9% |
| [231] | . Semantic Probabilistic Layers for Neuro-Symbolic Learning, In Advances in Neural Information Processing Systems 35 (NeurIPS), 2022. |
| [230] | . Neuro-Symbolic Entropy Regularization, In Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI), 2022. Oral full presentation, acceptance rate 36/712 = 5% |
| [229] | . Lossless Compression with Probabilistic Circuits, In Proceedings of the International Conference on Learning Representations (ICLR), 2022. Oral spotlight presentation, acceptance rate 176/3391 = 5.2% |
| [228] | . Solving Marginal MAP Exactly by Probabilistic Circuit Transformations, In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. |
| [227] | . PYLON: A PyTorch Framework for Learning with Constraints, In Proceedings of the 36th AAAI Conference on Artificial Intelligence (Demo Track), 2022. |
2021 | |
| [226] | . Tractable Regularization of Probabilistic Circuits, In Advances in Neural Information Processing Systems 34 (NeurIPS), 2021. Oral spotlight presentation, acceptance rate 340/9122 = 3.7% |
| [225] | . A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference, In Advances in Neural Information Processing Systems 34 (NeurIPS), 2021. Oral full presentation, acceptance rate 55/9122 = 0.6% |
| [224] | . Tractable Computation of Expected Kernels, In Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence (UAI), 2021. |
| [223] | . Probabilistic Generating Circuits, In Proceedings of the 38th International Conference on Machine Learning (ICML), 2021. Long presentation, acceptance rate 166/5513 = 3% |
| [222] | . Group Fairness by Probabilistic Modeling with Latent Fair Decisions, In Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021. |
| [221] | . Juice: A Julia Package for Logic and Probabilistic Circuits, In Proceedings of the 35th AAAI Conference on Artificial Intelligence (Demo Track), 2021. |
| [220] | . Logical Abstractions for Noisy Variational Quantum Algorithm Simulation, In Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2021. IEEE Micro top picks 2022 honorable mention |
2020 | |
| [219] | . Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations, In Advances in Neural Information Processing Systems 33 (NeurIPS), 2020. Oral spotlight presentation, acceptance rate 385/9454 = 4.1% |
| [218] | . Counterexample-Guided Learning of Monotonic Neural Networks, In Advances in Neural Information Processing Systems 33 (NeurIPS), 2020. |
| [217] | . Scaling Exact Inference for Discrete Probabilistic Programs, In Proc. ACM Program. Lang. (OOPSLA), ACM, 2020. ACM SIGPLAN distinguished paper award |
| [216] | . Relax, compensate and then integrate, In Proceedings of the ECML-PKDD Workshop on Deep Continuous-Discrete Machine Learning (DeCoDeML), 2020. |
| [215] | . Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing, In Proceedings of the 37th International Conference on Machine Learning (ICML), 2020. |
| [214] | . Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration, In Proceedings of the 19th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), 2020. |
| [213] | . Learning Fair Naive Bayes Classifiers by Discovering and Eliminating Discrimination Patterns, In Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020. |
2019 | |
| [212] | . On Tractable Computation of Expected Predictions, In Advances in Neural Information Processing Systems 32 (NeurIPS), 2019. |
| [211] | . Smoothing Structured Decomposable Circuits, In Advances in Neural Information Processing Systems 32 (NeurIPS), 2019. Oral spotlight presentation, acceptance rate 164/6743 = 2.4% |
| [210] | . Efficient Search-Based Weighted Model Integration, In Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), 2019. |
| [209] | . Generating and Sampling Orbits for Lifted Probabilistic Inference, In Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), 2019. Oral full presentation, acceptance rate 35/450 = 7% |
| [208] | . What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features, In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. |
| [207] | . Active Inductive Logic Programming for Code Search, In The 41st ACM/IEEE International Conference on Software Engineering (ICSE), 2019. |
| [206] | . Scalable Rule Learning in Probabilistic Knowledge Bases, In The 1st Conference On Automated Knowledge Base Construction (AKBC), 2019. |
| [205] | . Learning Logistic Circuits, In Proceedings of the 33rd Conference on Artificial Intelligence (AAAI), 2019. Oral full presentation, acceptance rate 460/7700 = 6% |
2018 | |
| [204] | . Approximate Knowledge Compilation by Online Collapsed Importance Sampling, In Advances in Neural Information Processing Systems 31 (NeurIPS), 2018. Oral full presentation, acceptance rate 30/4856 = 0.6% |
| [203] | . A Semantic Loss Function for Deep Learning with Symbolic Knowledge, In Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. |
2017 | |
| [202] | . A Semantic Loss Function for Deep Learning Under Weak Supervision, In NIPS 2017 Workshop on Learning with Limited Labeled Data: Weak Supervision and Beyond, 2017. LLD best paper award runner up |
| [201] | . A Semantic Loss Function for Deep Learning with Symbolic Knowledge, In CoRR, volume abs/1711.11157, 2017. |
| [200] | . Learning the Structure of Probabilistic Sentential Decision Diagrams, In Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence (UAI), 2017. Oral full presentation, acceptance rate 29/289 = 10% |
2015 | |
| [199] | . Lifted Generative Learning of Markov Logic Networks, In Machine Learning, volume 103, 2015. |
| [198] | . Tractable Learning for Complex Probability Queries, In Advances in Neural Information Processing Systems 28 (NIPS), 2015. |
| [197] | . Efficient Algorithms for Bayesian Network Parameter Learning from Incomplete Data, In Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence (UAI), 2015. Oral full presentation, acceptance rate 28/292 = 9% |
| [196] | . ProbLog2: Probabilistic logic programming, In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Demo Track, 2015. |
2014 | |
| [195] | . Tractable learning of liftable Markov logic networks, In Proceedings of the ICML-14 Workshop on Learning Tractable Probabilistic Models (LTPM), 2014. |
2013 | |
| [194] | . Lifted Inference and Learning in Statistical Relational Models, PhD thesis, KU Leuven, 2013. ECCAI Artificial Intelligence Dissertation Award Scientific prize IBM Belgium for Informatics |
| [193] | . On the complexity and approximation of binary evidence in lifted inference, In Advances in Neural Information Processing Systems 26 (NIPS), 2013. Oral spotlight presentation, acceptance rate 72/1420 = 5% |
| [192] | . Lifted generative parameter learning, In Statistical Relational AI (StaRAI) workshop, 2013. |
2012 | |
| [191] | . ProbLog2: From probabilistic programming to statistical relational learning, In Proceedings of the NIPS Probabilistic Programming Workshop, (Daniel Roy, Vikash Mansinghka, Noah Goodman, eds.), 2012. |
| [190] | . Lifted relax, compensate and then recover: From approximate to exact lifted probabilistic inference, In Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI) (Nando de Freitas, Kevin Murphy, eds.), 2012. |
| [189] | . Conditioning in first-order knowledge compilation and lifted probabilistic inference, In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, (Joerg Hoffmann, Bart Selman, eds.), AAAI Press, 2012. |
2011 | |
| [188] | . Lifted probabilistic inference by first-order knowledge compilation, In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI) (Toby Walsh, ed.), AAAI Press/International Joint Conferences on Artificial Intelligence, 2011. |
| [187] | . On the completeness of first-order knowledge compilation for lifted probabilistic inference, In Advances in Neural Information Processing Systems 24 (NIPS),, 2011. Oral full presentation, acceptance rate 20/1400 = 1.4% |
| [186] | . Inference in probabilistic logic programs using weighted CNF's, In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence (UAI), (Fabio Gagliardi Cozman, Avi Pfeffer, eds.), 2011. Oral full presentation, acceptance rate 24/285 = 8% |
| [185] | . ProbLog, Association for Logic Programming, 2011. ALP Newsletter |
2010 | |
| [184] | . DTProbLog: A decision-theoretic probabilistic Prolog, In Proceedings of the Twenty-fourth AAAI Conference on Artificial Intelligence, (Maria Fox, David Poole, eds.), AAAI Press, 2010. |