- Auto-Encoding Variational Bayes
- Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Neural Discrete Representation Learning
- Mathematics of Deep Learning
- Deep Clustering for Unsupervised Learning of Visual Features
- Phrase-Based & Neural Unsupervised Machine Translation
- World Models
- Can machine learning identify interesting mathematics? An exploration using empirically observed laws
- Discovering Structure in High-Dimensional Data Through Correlation Explanation
- Maximally Informative Hierarchical Representions of High-Dimensional Data
- Tighter Variational Bounds are Not Necessarily Better
- Beyond Sparsity: Tree Regularization of Deep Models for Interpretability
- Inverse molecular design using machine learning: Generative models for matter engineering
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- A simple neural network module for relational reasoning
- Non-local Neural Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation