Correctly manipulating program terms in a compiler is surprisingly diffi...
Automatic differentiation (AD) is conventionally understood as a family ...
The rapid rise in demand for training large neural network architectures...
Modern large-scale deep learning workloads highlight the need for parall...
Algebraic effects and handlers support composable and structured control...
We decompose reverse-mode automatic differentiation into (forward-mode)
...
We present a novel programming language design that attempts to combine ...
Multidimensional arrays (NDArrays) are a central abstraction in modern
s...
This paper presents the design, implementation, and evaluation of the Py...
We study set systems definable in graphs using variants of logic with
di...
Deep learning frameworks have often focused on either usability or speed...
The ability to perform pixel-wise semantic segmentation in real-time is ...
Since the emergence of Deep Neural Networks (DNNs) as a prominent techni...