Yoshua Bengio

Extendable Planning via Multiscale Diffusion AAAI 2026 Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models ICML 2025 HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models ICLR 2025 Rejecting Hallucinated State Targets during Planning ICML 2025 Structure Language Models for Protein Conformation Generation ICLR 2025 Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning ICLR 2025 Monte Carlo Tree Diffusion for System 2 Planning ICML 2025 VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text ICLR 2025 AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N ICML 2025 Geometric Signatures of Compositionality Across a Language Model’s Lifetime ACL 2025 On the Transfer of Object-Centric Representation Learning ICLR 2025 RL, but don’t do anything I wouldn’t do UAI 2025 Can a Bayesian Oracle Prevent Harm from an Agent? UAI 2025 Action abstractions for amortized sampling ICLR 2025 BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks ICLR 2025 MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation ICLR 2025 Towards Improving Exploration through Sibling Augmented GFlowNets ICLR 2025 Adaptive teachers for amortized samplers ICLR 2025 Ant Colony Sampling with GFlowNets for Combinatorial Optimization AISTATS 2025 AssembleFlow: Rigid Flow Matching with Inertial Frames for Molecular Assembly ICLR 2025 Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets ICLR 2025 Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold ICLR 2025 Towards a Formal Theory of Representational Compositionality ICML 2025 Improving Gradient-Guided Nested Sampling for Posterior Inference ICML 2024 Amortizing intractable inference in diffusion models for vision, language, and control NIPS 2024 Pre-Training and Fine-Tuning Generative Flow Networks ICLR 2024 Tree Cross Attention ICLR 2024 Delta-AI: Local objectives for amortized inference in sparse graphical models ICLR 2024 Amortizing intractable inference in large language models ICLR 2024 Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning ICLR 2024 Local Search GFlowNets ICLR 2024 Iterated Denoising Energy Matching for Sampling from Boltzmann Densities ICML 2024 Regeneration Learning: A Learning Paradigm for Data Generation AAAI 2024 Simulation-Free Schrödinger Bridges via Score and Flow Matching AISTATS 2024 Cycle Consistency Driven Object Discovery ICLR 2024 Object centric architectures enable efficient causal representation learning ICLR 2024 PhyloGFN: Phylogenetic inference with generative flow networks ICLR 2024 Memory Efficient Neural Processes via Constant Memory Attention Block ICML 2024 Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving NIPS 2024 RGFN: Synthesizable Molecular Generation Using GFlowNets NIPS 2024 Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization ICLR 2024 Improved off-policy training of diffusion samplers NIPS 2024 Trajectory Flow Matching with Applications to Clinical Time Series Modelling NIPS 2024 Expected flow networks in stochastic environments and two-player zero-sum games ICLR 2024 Discrete Probabilistic Inference as Control in Multi-path Environments UAI 2024 PhAST: Physics-Aware, Scalable, and Task-Specific GNNs for Accelerated Catalyst Design JMLR 2024 Learning to Scale Logits for Temperature-Conditional GFlowNets ICML 2024 SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data NIPS 2023 The Effect of Diversity in Meta-Learning AAAI 2023 Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization for Heterogeneous Representational Coarseness AAAI 2023 Predictive Inference with Feature Conformal Prediction ICLR 2023 Latent State Marginalization as a Low-cost Approach for Improving Exploration ICLR 2023 Robust and Controllable Object-Centric Learning through Energy-based Models ICLR 2023 GFlowNets and variational inference ICLR 2023 Generative Augmented Flow Networks ICLR 2023 Equivariance with Learned Canonicalization Functions ICML 2023 Multi-Objective GFlowNets ICML 2023 GFlowNet-EM for Learning Compositional Latent Variable Models ICML 2023 FAENet: Frame Averaging Equivariant GNN for Materials Modeling ICML 2023 Interventional Causal Representation Learning ICML 2023 Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning ICML 2023 MixupE: Understanding and improving Mixup from directional derivative perspective UAI 2023 Stochastic Generative Flow Networks UAI 2023 A theory of continuous generative flow networks ICML 2023 GFlowOut: Dropout with Generative Flow Networks ICML 2023 Learning GFlowNets From Partial Episodes For Improved Convergence And Stability ICML 2023 Better Training of GFlowNets with Local Credit and Incomplete Trajectories ICML 2023 Hyena Hierarchy: Towards Larger Convolutional Language Models ICML 2023 Discrete Key-Value Bottleneck ICML 2023 Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning ICLR 2023 Latent Bottlenecked Attentive Neural Processes ICLR 2023 Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context NIPS 2023 Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets NIPS 2023 Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions NIPS 2023 Reusable Slotwise Mechanisms NIPS 2023 Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL NIPS 2023 Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network NIPS 2023 HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution NIPS 2023 GEO-Bench: Toward Foundation Models for Earth Monitoring NIPS 2023 DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets NIPS 2023 Combining Parameter-efficient Modules for Task-level Generalisation EACL 2023 GFlowNet Foundations JMLR 2023 Benchmarking Graph Neural Networks JMLR 2023 Neural Attentive Circuits NIPS 2022 ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods ICLR 2022 Chunked Autoregressive GAN for Conditional Waveform Synthesis ICLR 2022 Graph Neural Networks with Learnable Structural and Positional Representations ICLR 2022 Coordination Among Neural Modules Through a Shared Global Workspace ICLR 2022 Compositional Attention: Disentangling Search and Retrieval ICLR 2022 Properties from mechanisms: an equivariance perspective on identifiable representation learning ICLR 2022 Unifying Likelihood-free Inference with Black-box Optimization and Beyond ICLR 2022 Continuous-Time Meta-Learning with Forward Mode Differentiation ICLR 2022 Building Robust Ensembles via Margin Boosting ICML 2022 Generative Flow Networks for Discrete Probabilistic Modeling ICML 2022 Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL UAI 2022 Bayesian structure learning with generative flow networks UAI 2022 Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints NIPS 2022 Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning NIPS 2022 Trajectory balance: Improved credit assignment in GFlowNets NIPS 2022 Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning NIPS 2022 Weakly Supervised Representation Learning with Sparse Perturbations NIPS 2022 Is a Modular Architecture Enough? NIPS 2022 MAgNet: Mesh Agnostic Neural PDE Solver NIPS 2022 Multi-scale Feature Learning Dynamics: Insights for Double Descent ICML 2022 Biological Sequence Design with GFlowNets ICML 2022 Towards Scaling Difference Target Propagation by Learning Backprop Targets ICML 2022 VIM: Variational Independent Modules for Video Prediction CLEAR 2022 Systematic generalisation with group invariant predictions ICLR 2021 Object-Centric Image Generation from Layouts AAAI 2021 CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning ICLR 2021 Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation NIPS 2021 FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters ICCV 2021 Neural Production Systems NIPS 2021 Dynamic Inference with Neural Interpreters NIPS 2021 The Causal-Neural Connection: Expressiveness, Learnability, and Inference NIPS 2021 Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization NIPS 2021 Discrete-Valued Neural Communication NIPS 2021 A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning NIPS 2021 Gradient Starvation: A Learning Proclivity in Neural Networks NIPS 2021 Recurrent Independent Mechanisms ICLR 2021 Predicting Infectiousness for Proactive Contact Tracing ICLR 2021 Saliency is a Possible Red Herring When Diagnosing Poor Generalization ICLR 2021 Learning Neural Generative Dynamics for Molecular Conformation Generation ICLR 2021 Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments ICLR 2021 Fast And Slow Learning Of Recurrent Independent Mechanisms ICLR 2021 RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs ICLR 2021 Spatially Structured Recurrent Modules ICLR 2021 An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming ICML 2021 An Analysis of the Adaptation Speed of Causal Models AISTATS 2021 Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers AISTATS 2021 GraphMix: Improved Training of GNNs for Semi-Supervised Learning AAAI 2021 Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting AAAI 2021 Visual Concept Reasoning Networks AAAI 2021 hBERT + BiasCorp - Fighting Racism on the Web EACL 2021 Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models AAAI 2021 Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies AAAI 2021 Revisiting Fundamentals of Experience Replay ICML 2020 Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning ICML 2020 Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules ICML 2020 Small-GAN: Speeding up GAN Training using Core-Sets ICML 2020 Perceptual Generative Autoencoders ICML 2020 Experience Grounds Language EMNLP 2020 On the interplay between noise and curvature and its effect on optimization and generalization AISTATS 2020 Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives ICLR 2020 Untangling tradeoffs between recurrence and self-attention in artificial neural networks NIPS 2020 Hybrid Models for Learning to Branch NIPS 2020 Your GAN is Secretly an Energy-based Model and You Should Use Discriminator Driven Latent Sampling NIPS 2020 N-BEATS: Neural basis expansion analysis for interpretable time series forecasting ICLR 2020 Learning the Arrow of Time for Problems in Reinforcement Learning ICLR 2020 Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach ACL 2020 The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget ICLR 2020 DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning ECCV 2020 Compositional Generalization by Factorizing Alignment and Translation ACL 2020 A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms ICLR 2020 Combating False Negatives in Adversarial Imitation Learning (Student Abstract) AAAI 2020 Interpolation Consistency Training for Semi-supervised Learning IJCAI 2019 Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input NIPS 2019 MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis NIPS 2019 Unsupervised State Representation Learning in Atari NIPS 2019 Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics NIPS 2019 Variational Temporal Abstraction NIPS 2019 How to Initialize your Network? Robust Initialization for WeightNorm & ResNets NIPS 2019 Gradient based sample selection for online continual learning NIPS 2019 On Adversarial Mixup Resynthesis NIPS 2019 Wasserstein Dependency Measure for Representation Learning NIPS 2019 Towards Non-Saturating Recurrent Units for Modelling Long-Term Dependencies AAAI 2019 Combined Reinforcement Learning via Abstract Representations AAAI 2019 Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study ACL 2019 Interactive Language Learning by Question Answering EMNLP 2019 Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization ICCV 2019 Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction ICCV 2019 Modeling the Long Term Future in Model-Based Reinforcement Learning ICLR 2019 An Empirical Study of Example Forgetting during Deep Neural Network Learning ICLR 2019 Recall Traces: Backtracking Models for Efficient Reinforcement Learning ICLR 2019 Probabilistic Planning with Sequential Monte Carlo methods ICLR 2019 InfoBot: Transfer and Exploration via the Information Bottleneck ICLR 2019 BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning ICLR 2019 On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length ICLR 2019 Learning deep representations by mutual information estimation and maximization ICLR 2019 h-detach: Modifying the LSTM Gradient Towards Better Optimization ICLR 2019 Deep Graph Infomax ICLR 2019 Quaternion Recurrent Neural Networks ICLR 2019 Adversarial Domain Adaptation for Stable Brain-Machine Interfaces ICLR 2019 State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations ICML 2019 GMNN: Graph Markov Neural Networks ICML 2019 On the Spectral Bias of Neural Networks ICML 2019 Manifold Mixup: Better Representations by Interpolating Hidden States ICML 2019 Interactive Language Learning by Question Answering IJCNLP 2019 Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks INTERSPEECH 2019 Speech Model Pre-Training for End-to-End Spoken Language Understanding INTERSPEECH 2019 Learning Speaker Representations with Mutual Information INTERSPEECH 2019 Straight to the Tree: Constituency Parsing with Neural Syntactic Distance ACL 2018 Deep Complex Networks ICLR 2018 Residual Connections Encourage Iterative Inference ICLR 2018 Twin Networks: Matching the Future for Sequence Generation ICLR 2018 Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning ICLR 2018 Graph Attention Networks ICLR 2018 Fraternal Dropout ICLR 2018 Boundary Seeking GANs ICLR 2018 Commonsense mining as knowledge base completion? A study on the impact of novelty NAACL 2018 Learning Hierarchical Structures On-The-Fly with a Recurrent-Recursive Model for Sequences ACL 2018 Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations JMLR 2018 HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering EMNLP 2018 Mutual Information Neural Estimation ICML 2018 Focused Hierarchical RNNs for Conditional Sequence Processing ICML 2018 Twin Regularization for Online Speech Recognition INTERSPEECH 2018 Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition INTERSPEECH 2018 Neural Models for Key Phrase Extraction and Question Generation ACL 2018 Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding NIPS 2018 Bayesian Model-Agnostic Meta-Learning NIPS 2018 Image-to-image translation for cross-domain disentanglement NIPS 2018 MetaGAN: An Adversarial Approach to Few-Shot Learning NIPS 2018 Dendritic cortical microcircuits approximate the backpropagation algorithm NIPS 2018 Improving Speech Recognition by Revising Gated Recurrent Units INTERSPEECH 2017 Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net NIPS 2017 Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space CVPR 2017 GibbsNet: Iterative Adversarial Inference for Deep Graphical Models NIPS 2017 Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses ACL 2017 A Closer Look at Memorization in Deep Networks ICML 2017 Sharp Minima Can Generalize For Deep Nets ICML 2017 Plan, Attend, Generate: Planning for Sequence-to-Sequence Models NIPS 2017 Z-Forcing: Training Stochastic Recurrent Networks NIPS 2017 Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition INTERSPEECH 2017 Unitary Evolution Recurrent Neural Networks ICML 2016 Bidirectional Helmholtz Machines ICML 2016 Noisy Activation Functions ICML 2016 Architectural Complexity Measures of Recurrent Neural Networks NIPS 2016 Professor Forcing: A New Algorithm for Training Recurrent Networks NIPS 2016 A Character-level Decoder without Explicit Segmentation for Neural Machine Translation ACL 2016 Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus ACL 2016 Pointing the Unknown Words ACL 2016 Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks INTERSPEECH 2016 Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism NAACL 2016 On Multiplicative Integration with Recurrent Neural Networks NIPS 2016 Knowledge Matters: Importance of Prior Information for Optimization JMLR 2016 Binarized Neural Networks NIPS 2016 Deconstructing the Ladder Network Architecture ICML 2016 Gated Feedback Recurrent Neural Networks ICML 2015 BilBOWA: Fast Bilingual Distributed Representations without Word Alignments ICML 2015 Show, Attend and Tell: Neural Image Caption Generation with Visual Attention ICML 2015 On Using Very Large Target Vocabulary for Neural Machine Translation ACL 2015 Equilibrated adaptive learning rates for non-convex optimization NIPS 2015 On Using Very Large Target Vocabulary for Neural Machine Translation IJCNLP 2015 Attention-Based Models for Speech Recognition NIPS 2015 BinaryConnect: Training Deep Neural Networks with binary weights during propagations NIPS 2015 A Recurrent Latent Variable Model for Sequential Data NIPS 2015 Identifying and attacking the saddle point problem in high-dimensional non-convex optimization NIPS 2014 Deep Generative Stochastic Networks Trainable by Backprop ICML 2014 Marginalized Denoising Auto-encoders for Nonlinear Representations ICML 2014 On the Number of Linear Regions of Deep Neural Networks NIPS 2014 Generative Adversarial Nets NIPS 2014 Iterative Neural Autoregressive Distribution Estimator NADE-k NIPS 2014 How transferable are features in deep neural networks? NIPS 2014 Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation EMNLP 2014 What Regularized Auto-Encoders Learn from the Data-Generating Distribution JMLR 2014 Maxout Networks ICML 2013 Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions AISTATS 2013 Better Mixing via Deep Representations ICML 2013 Multi-Prediction Deep Boltzmann Machines NIPS 2013 Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs NIPS 2013 Generalized Denoising Auto-Encoders as Generative Models NIPS 2013 On the difficulty of training recurrent neural networks ICML 2013 Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing AISTATS 2012 Deep Learning for NLP (without Magic) ACL 2012 Random Search for Hyper-Parameter Optimization JMLR 2012 Learning Algorithms for the Classification Restricted Boltzmann Machine JMLR 2012 Deep Sparse Rectifier Neural Networks AISTATS 2011 Discussion of “The Neural Autoregressive Distribution Estimator” AISTATS 2011 Shallow vs. Deep Sum-Product Networks NIPS 2011 Algorithms for Hyper-Parameter Optimization NIPS 2011 The Manifold Tangent Classifier NIPS 2011 On Tracking The Partition Function NIPS 2011 A Spike and Slab Restricted Boltzmann Machine AISTATS 2011 Deep Learners Benefit More from Out-of-Distribution Examples AISTATS 2011 Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines AISTATS 2010 Why Does Unsupervised Pre-training Help Deep Learning? JMLR 2010 Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion JMLR 2010 Understanding the difficulty of training deep feedforward neural networks AISTATS 2010 Word Representations: A Simple and General Method for Semi-Supervised Learning ACL 2010 Why Does Unsupervised Pre-training Help Deep Learning? AISTATS 2010 Slow, Decorrelated Features for Pretraining Complex Cell-like Networks NIPS 2009 Exploring Strategies for Training Deep Neural Networks JMLR 2009 Quadratic Features and Deep Architectures for Chunking NAACL 2009 Incorporating Functional Knowledge in Neural Networks JMLR 2009 An Infinite Factor Model Hierarchy Via a Noisy-Or Mechanism NIPS 2009 Augmented Functional Time Series Representation and Forecasting with Gaussian Processes NIPS 2007 Topmoumoute Online Natural Gradient Algorithm NIPS 2007 Learning the 2-D Topology of Images NIPS 2007 Greedy Layer-Wise Training of Deep Networks NIPS 2006 No Unbiased Estimator of the Variance of K-Fold Cross-Validation JMLR 2004 Unsupervised Sense Disambiguation Using Bilingual Probabilistic Models ACL 2004 Extensions to Metric-Based Model Selection JMLR 2003 A Neural Probabilistic Language Model JMLR 2003