Alert button
Picture for Richard Zemel

Richard Zemel

Alert button

Disentanglement and Generalization Under Correlation Shifts

Dec 29, 2021
Christina M. Funke, Paul Vicol, Kuan-Chieh Wang, Matthias Kümmerer, Richard Zemel, Matthias Bethge

Figure 1 for Disentanglement and Generalization Under Correlation Shifts
Figure 2 for Disentanglement and Generalization Under Correlation Shifts
Figure 3 for Disentanglement and Generalization Under Correlation Shifts
Figure 4 for Disentanglement and Generalization Under Correlation Shifts
Viaarxiv icon

Identifying and Benchmarking Natural Out-of-Context Prediction Problems

Oct 25, 2021
David Madras, Richard Zemel

Figure 1 for Identifying and Benchmarking Natural Out-of-Context Prediction Problems
Figure 2 for Identifying and Benchmarking Natural Out-of-Context Prediction Problems
Figure 3 for Identifying and Benchmarking Natural Out-of-Context Prediction Problems
Figure 4 for Identifying and Benchmarking Natural Out-of-Context Prediction Problems
Viaarxiv icon

Online Unsupervised Learning of Visual Representations and Categories

Sep 13, 2021
Mengye Ren, Tyler R. Scott, Michael L. Iuzzolino, Michael C. Mozer, Richard Zemel

Figure 1 for Online Unsupervised Learning of Visual Representations and Categories
Figure 2 for Online Unsupervised Learning of Visual Representations and Categories
Figure 3 for Online Unsupervised Learning of Visual Representations and Categories
Figure 4 for Online Unsupervised Learning of Visual Representations and Categories
Viaarxiv icon

Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data

Jul 19, 2021
Jacob Kelly, Richard Zemel, Will Grathwohl

Figure 1 for Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
Figure 2 for Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
Figure 3 for Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
Figure 4 for Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data
Viaarxiv icon

NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation

Jul 04, 2021
Xiaohui Zeng, Raquel Urtasun, Richard Zemel, Sanja Fidler, Renjie Liao

Figure 1 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Figure 2 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Figure 3 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Figure 4 for NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
Viaarxiv icon

NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation

Jun 25, 2021
Xiaohui Zeng, Raquel Urtasun, Richard Zemel, Sanja Fidler, Renjie Liao

Figure 1 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Figure 2 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Figure 3 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Figure 4 for NP-DRAW: A Non-Parametric Structured Latent Variable Modelfor Image Generation
Viaarxiv icon

Learning a Universal Template for Few-shot Dataset Generalization

May 14, 2021
Eleni Triantafillou, Hugo Larochelle, Richard Zemel, Vincent Dumoulin

Figure 1 for Learning a Universal Template for Few-shot Dataset Generalization
Figure 2 for Learning a Universal Template for Few-shot Dataset Generalization
Figure 3 for Learning a Universal Template for Few-shot Dataset Generalization
Figure 4 for Learning a Universal Template for Few-shot Dataset Generalization
Viaarxiv icon

Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes

Apr 23, 2021
James Lucas, Juhan Bae, Michael R. Zhang, Stanislav Fort, Richard Zemel, Roger Grosse

Figure 1 for Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
Figure 2 for Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
Figure 3 for Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
Figure 4 for Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes
Viaarxiv icon

A Computational Framework for Slang Generation

Feb 03, 2021
Zhewei Sun, Richard Zemel, Yang Xu

Figure 1 for A Computational Framework for Slang Generation
Figure 2 for A Computational Framework for Slang Generation
Figure 3 for A Computational Framework for Slang Generation
Figure 4 for A Computational Framework for Slang Generation
Viaarxiv icon

A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks

Dec 14, 2020
Renjie Liao, Raquel Urtasun, Richard Zemel

Figure 1 for A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
Figure 2 for A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
Figure 3 for A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
Figure 4 for A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks
Viaarxiv icon