activity
20182022
most citedLearning Robust Representations via Multi-View Information Bottleneck

82 citations · 142 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG202223 cited

Solving math word problems with process- and outcome-based feedback

Jonathan Uesato, Nate Kushman, Ramana Kumar +6

Recent work has shown that asking language models to generate reasoning steps improves performance on many reasoning tasks. When moving beyond prompting, this raises the question o…

cs.LG20201 cited

Interpreting Spatially Infinite Generative Models

Chaochao Lu, Richard E. Turner, Yingzhen Li +1

Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the traini…

cs.CV202036 cited

Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data

Sebastian Lunz, Yingzhen Li, Andrew Fitzgibbon +1

Recent work has shown the ability to learn generative models for 3D shapes from only unstructured 2D images. However, training such models requires differentiating through the rast…

cs.LG202082 cited

Learning Robust Representations via Multi-View Information Bottleneck

Marco Federici, Anjan Dutta, Patrick Forré +2

The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for pr…

stat.ML2018

Inverting Supervised Representations with Autoregressive Neural Density Models

Charlie Nash, Nate Kushman, Christopher K. I. Williams

We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative in…

cs.LG2018

Constructing Unrestricted Adversarial Examples with Generative Models

Yang Song, Rui Shu, Nate Kushman +1

Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this typ…