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