The quality of training data impacts the performance of pre-trained larg...
Machine learning models – including prominent zero-shot models – are oft...
Weak supervision (WS) is a rich set of techniques that produce pseudolab...
Weak supervision (WS) is a powerful method to build labeled datasets for...
Weak supervision (WS) frameworks are a popular way to bypass hand-labeli...
Most existing neural architecture search (NAS) benchmarks and algorithms...
An important goal of neural architecture search (NAS) is to automate-awa...
Neural Machine Translation (NMT) systems are typically evaluated using
a...
This paper explores the scenarios under which an attacker can claim that...
The interplay between inter-neuronal network topology and cognition has ...
Kernel sparsity ("dying ReLUs") and lack of diversity are commonly obser...