Augustus Odena
Google Brain at Google
Large pre-trained language models perform remarkably well on tasks that ...
This paper explores the limits of the current generation of large langua...
Given a quantum circuit, a quantum computer can sample the output
distri...
We propose a novel type of balanced clustering algorithm to approximate
...
Program synthesis is challenging largely because of the difficulty of se...
We introduce a simple (one line of code) modification to the Generative
...
We introduce the notion of property signatures, a representation for pro...
Recent work has increased the performance of Generative Adversarial Netw...
We introduce a new local sparse attention layer that preserves
two-dimen...
Recent work by Brock et al. (2018) suggests that Generative Adversarial
...
Generative Adversarial Networks (GANs) are known to be difficult to trai...
Broad adoption of machine learning techniques has increased privacy conc...
We propose a rejection sampling scheme using the discriminator of a GAN ...
We explore a new way to evaluate generative models using insights from
e...
Machine learning models are notoriously difficult to interpret and debug...
In this paper, we propose the Self-Attention Generative Adversarial Netw...
Semi-supervised learning (SSL) provides a powerful framework for leverag...
Recent work (Pennington et al, 2017) suggests that controlling the entir...
Machine learning models are often used at test-time subject to constrain...
Synthesizing high resolution photorealistic images has been a long-stand...
We extend Generative Adversarial Networks (GANs) to the semi-supervised
...
Asynchronous distributed stochastic gradient descent methods have troubl...