Network quantization has gained increasing attention with the rapid growth of large pre-
trained language models~(PLMs). However, most existing quantization methods for PLMs …

The emergence of accurate open large language models (LLMs) has led to a race towards
quantization techniques for such models enabling execution on end-user devices. In this …

In this paper, we compress convolutional neural network (CNN) weights post-training via
transform quantization. Previous CNN quantization techniques tend to ignore the joint …

Abstract Model compression has been widely adopted to obtain light-weighted deep neural
networks. Most prevalent methods, however, require fine-tuning with sufficient training data …

Abstract Deep Neural Networks (DNNs) enjoy the welfare of convolution, while also bearing
huge computational pressure. Therefore, model compression techniques are used to …

Implementing deep convolutional neural networks (CNNs) with boolean arithmetic is ideal
for eliminating the notoriously high computational expense of deep learning models …

The computing power of various Internet of Things (IoT) devices is quite different. To enable
IoT devices with lower computing power to perform machine learning, all nodes can only …

Recent emerged quantization technique (ie, using low bit-width fixed-point data instead of
high bit-width floating-point data) has been applied to inference of deep neural networks for …

Video Snapshot Compressive Imaging (SCI) aims to use a low-speed 2D camera to capture
high-speed scene as snapshot compressed measurements, followed by a reconstruction …

While previous network compression methods achieve great success, most of them rely on
the abundant training data which is, unfortunately, often unavailable in practice due to some …