The exponential increase in generated data as well as the advances in high-performance
computing has paved the way for the use of complex machine learning methods. Indeed, the …

With the advent of deep learning, progressively larger neural networks have been designed
to solve complex tasks. We take advantage of these capacity-rich models to lower the cost of …

Neural networks (NNs) have achieved superhuman accuracy in multiple tasks, but NNs
predictions' certainty is often debatable, especially if confronted with out of training …

State-of-the-art large language models (LLMs) have become indispensable tools for various
tasks. However, training LLMs to serve as effective assistants for humans requires careful …

Pre-trained language models (PLMs) are often deployed as cloud services, enabling users
to upload textual data and perform inference remotely. However, users' personal text often …

Rapid advancements over the years have helped machine learning models reach
previously hard-to-achieve goals, sometimes even exceeding human capabilities. However …

Pre-trained language models (PLMs) have achieved remarkable results on NLP tasks but at
the expense of huge parameter sizes and the consequent computational costs. In this paper …

The widespread adoption of large language models such as ChatGPT and Bard has led to
unprecedented demand for these technologies. The burgeoning cost of inference for ever …

As language models increase in size by the day, methods for efficient inference are critical to
leveraging their capabilities for various applications. Prior work has investigated techniques …

Ensembles of separate neural networks (NNs) have shown superior accuracy and
confidence calibration over single NN across tasks. Recent methods compress ensembles …