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 & contextIan Goodfellow
Generative models
Training a generator through competition with a discriminator.
Goodfellow’s research connects generative modeling with the reliability of neural networks. Generative adversarial networks learn through a contest between two models; his work on adversarial examples examines how small input changes can reveal brittle model behavior.
Selected work
10 papers
2014 · Generative models
Explaining and Harnessing Adversarial Examples
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2013 · Language models
Intriguing properties of neural networks
Selected research in language models, generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2019 · Generative models
MixMatch: A Holistic Approach to Semi-Supervised Learning
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2025 · Generative models
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2024 · Generative models
TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2020 · Generative models
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Selected research in generative models, ai evaluation. Read the full paper, including the methods, experiments, and reported results.
Paper & context2020 · Generative models
Creating High Resolution Images with a Latent Adversarial Generator
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2019 · Generative models
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition
Selected research in generative models. Read the full paper, including the methods, experiments, and reported results.
Paper & context2019 · Generative models
A Research Agenda: Dynamic Models to Defend Against Correlated Attacks
Selected research in generative models. 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