Aaron Courville

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks ICML 2025 The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning ICML 2025 VinePPO: Refining Credit Assignment in RL Training of LLMs ICML 2025 Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study ICLR 2025 Neuroplastic Expansion in Deep Reinforcement Learning ICLR 2025 Forgetting Transformer: Softmax Attention with a Forget Gate ICLR 2025 Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models ICLR 2025 FLAM: Frame-Wise Language-Audio Modeling ICML 2025 Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL ICLR 2025 Advantage Alignment Algorithms ICLR 2025 Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn ICML 2025 SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision ECCV 2024 LOQA: Learning with Opponent Q-Learning Awareness ICLR 2024 The Curse of Diversity in Ensemble-Based Exploration ICLR 2024 Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization ICLR 2024 GenRL: Multimodal-foundation world models for generalization in embodied agents NIPS 2024 Adaptive Accompaniment with ReaLchords ICML 2024 In value-based deep reinforcement learning, a pruned network is a good network ICML 2024 Modeling Caption Diversity in Contrastive Vision-Language Pretraining ICML 2024 SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning ECCV 2024 Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier ICLR 2023 Sparse Universal Transformer EMNLP 2023 Bigger, Better, Faster: Human-level Atari with human-level efficiency ICML 2023 Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels ICML 2023 Investigating Multi-task Pretraining and Generalization in Reinforcement Learning ICLR 2023 Latent State Marginalization as a Low-cost Approach for Improving Exploration ICLR 2023 Simplicial Embeddings in Self-Supervised Learning and Downstream Classification ICLR 2023 Generative Augmented Flow Networks ICLR 2023 Unsupervised Dependency Graph Network ACL 2022 Generative Flow Networks for Discrete Probabilistic Modeling ICML 2022 The Primacy Bias in Deep Reinforcement Learning ICML 2022 Fortuitous Forgetting in Connectionist Networks ICLR 2022 Chunked Autoregressive GAN for Conditional Waveform Synthesis ICLR 2022 Learning to Dequantise with Truncated Flows ICLR 2022 MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling ICLR 2022 DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization ICLR 2022 Unifying Likelihood-free Inference with Black-box Optimization and Beyond ICLR 2022 VIM: Variational Independent Modules for Video Prediction CLEAR 2022 Multi-Label Iterated Learning for Image Classification With Label Ambiguity CVPR 2022 On the Compositional Generalization Gap of In-Context Learning EMNLP 2022 Building Robust Ensembles via Margin Boosting ICML 2022 StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling ACL 2021 StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling IJCNLP 2021 Continuous Coordination As a Realistic Scenario for Lifelong Learning ICML 2021 Out-of-Distribution Generalization via Risk Extrapolation (REx) ICML 2021 Generative Compositional Augmentations for Scene Graph Prediction ICCV 2021 Understanding by Understanding Not: Modeling Negation in Language Models NAACL 2021 Haptics-based Curiosity for Sparse-reward Tasks CORL 2021 Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization? ICML 2021 Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle NAACL 2021 Learning Task Decomposition with Ordered Memory Policy Network ICLR 2021 Integrating Categorical Semantics into Unsupervised Domain Translation ICLR 2021 Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization ICLR 2021 Iterated learning for emergent systematicity in VQA ICLR 2021 Systematic generalisation with group invariant predictions ICLR 2021 Data-Efficient Reinforcement Learning with Self-Predictive Representations ICLR 2021 Neural Approximate Sufficient Statistics for Implicit Models ICLR 2021 Countering Language Drift with Seeded Iterated Learning ICML 2020 Detecting Semantic Anomalies AAAI 2020 Stochastic Neural Network with Kronecker Flow AISTATS 2020 Supervised Seeded Iterated Learning for Interactive Language Learning EMNLP 2020 Recursive Top-Down Production for Sentence Generation with Latent Trees EMNLP 2020 On Bonus Based Exploration Methods In The Arcade Learning Environment ICLR 2020 AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation ICML 2020 Systematic Generalization: What Is Required and Can It Be Learned? ICLR 2019 Improved Conditional VRNNs for Video Prediction ICCV 2019 Batch Weight for Domain Adaptation With Mass Shift ICCV 2019 Hierarchical Importance Weighted Autoencoders ICML 2019 On the Spectral Bias of Neural Networks ICML 2019 Probability Distillation: A Caveat and Alternatives UAI 2019 Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks ICLR 2019 Neural Language Modeling by Jointly Learning Syntax and Lexicon ICLR 2018 Sim-to-Real Transfer with Neural-Augmented Robot Simulation CORL 2018 Mutual Information Neural Estimation ICML 2018 Neural Autoregressive Flows ICML 2018 Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data ICML 2018 Straight to the Tree: Constituency Parsing with Neural Syntactic Distance ACL 2018 Piecewise Latent Variables for Neural Variational Text Processing EMNLP 2017 A Closer Look at Memorization in Deep Networks ICML 2017 End-to-end optimization of goal-driven and visually grounded dialogue systems IJCAI 2017 GuessWhat?! Visual Object Discovery Through Multi-Modal Dialogue CVPR 2017 A Dataset and Exploration of Models for Understanding Video Data Through Fill-In-The-Blank Question-Answering CVPR 2017 Dynamic Capacity Networks ICML 2016 Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus ACL 2016 Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks INTERSPEECH 2016 Deconstructing the Ladder Network Architecture ICML 2016 Show, Attend and Tell: Neural Image Caption Generation with Visual Attention ICML 2015 Describing Videos by Exploiting Temporal Structure ICCV 2015 Generative Adversarial Nets NIPS 2014 Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions AISTATS 2013 Multi-Prediction Deep Boltzmann Machines NIPS 2013 Maxout Networks ICML 2013 A Spike and Slab Restricted Boltzmann Machine AISTATS 2011 Why Does Unsupervised Pre-training Help Deep Learning? AISTATS 2010 Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines AISTATS 2010 Why Does Unsupervised Pre-training Help Deep Learning? JMLR 2010 Interacting Markov Random Fields for Simultaneous Terrain Modeling and Obstacle Detection RSS 2005