Machine learning powers diverse services in industry including search, translation,
recommendation systems, and security. The scale and importance of these models require that they …

Frameworks for writing, compiling, and optimizing deep learning (DL) models have recently
enabled progress in areas like computer vision and natural language processing. Extending …

A $\textit{neural surrogate of a program}$ is a neural network that mimics the behavior of a
program. Researchers have used these neural surrogates to automatically tune program …

… JARED ROESCH, Unversity of Washington STEVEN LYUBOMIRSKY, Unversity of Washington
MARISA KIRISAME, Unversity of Washington JOSH POLLOCK, Unversity of Washington LOGAN …

With increasing commercial applications of vanadium flow batteries (VFB), containerised
VFB systems are gaining attention as they can be mass produced and easily transported and …

Ever since Shinagawa, Kunii, and Kergosien gave the first algorithm for computing Reeb
graphs [SKK91], they have become an important technique in computational topology. Their …

Ketogenic diets (KDs) are a popular tool used for weight management. Studies in mice have
demonstrated that KDs reduce food intake, increase energy expenditure and cause weight …

In 2017, Eisenbrand and Weismantel improved a longstanding runtime bound for pseudopolynomial
integer programming algorithms with a fixed number of constraints, m, most notably …

Program embeddings are used to solve tasks such as \textit{code clone detection} and \textit{semantic
labeling}. Solutions to these \textit{semantic tasks} should be invariant to …

Abstract Models that embed programs as vectors are commonly used to predict properties
of programs. A common desiderata of a learned program embedding space is that similar …