Language models (LMs) are increasingly being used in open-ended contexts...
Selecting a suitable training dataset is crucial for both general-domain...
Language models (LMs) are becoming the foundation for almost all major
l...
We present a methodology for modifying the behavior of a classifier by
d...
We show how fitting sparse linear models over learned deep feature
repre...
We develop a methodology for assessing the robustness of models to
subpo...
We study the roots of algorithmic progress in deep policy gradient algor...
Building rich machine learning datasets in a scalable manner often
neces...
Dataset replication is a useful tool for assessing whether improvements ...
We show that the basic classification framework alone can be used to tac...
We show that the basic classification framework alone can be used to tac...
Many applications of machine learning require models that are human-alig...
Adversarial examples have attracted significant attention in machine
lea...
We study how the behavior of deep policy gradient algorithms reflects th...
We provide a new understanding of the fundamental nature of adversariall...
Batch Normalization (BatchNorm) is a widely adopted technique that enabl...
Machine learning models are often susceptible to adversarial perturbatio...
A fundamental, and still largely unanswered, question in the context of
...
Traditional image and video compression algorithms rely on hand-crafted
...
Connectomics is an emerging field in neuroscience that aims to reconstru...
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels a...