2014 · Deep learning
Neural Machine Translation by Jointly Learning to Align and Translate
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & contextYoshua Bengio
Learning distributed representations that can support generalization.
Bengio studies how learned representations support reasoning and generalization. His coauthored work includes neural attention for translation, generative adversarial networks, and graph attention. More recent work examines how to make capable AI systems reliable and safe.
Selected work
10 papers
2014 · Generative models
Generative Adversarial Networks
Generative adversarial networks train a generator and a discriminator together. Their competing objectives can learn to synthesize data.
Paper & context2012 · Deep learning
Representation Learning: A Review and New Perspectives
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2017 · Deep learning
Graph Attention Networks
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Deep learning
AI Safety: Not Optional, Not Later
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Deep learning
How to Verify Probabilistic Consistency of Predictive Models
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Deep learning
Bayesian Symbolic Regression with Entropic Reinforcement Learning
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Deep learning
Towards Trustworthy Physical AI: From Theory to Practice Across Life Cycle
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Deep learning
The 2026 Singapore Consensus on Global AI Safety Research Priorities
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & context2026 · Deep learning
Open Technical Problems in Open-Weight AI Model Risk Management
Selected research in deep learning. Read the full paper, including the methods, experiments, and reported results.
Paper & contextAn independent editorial profile. Inclusion does not imply Council membership or endorsement. Research is collaborative; coauthorship does not imply sole credit.
Selection & sources