Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

Lightweight deep convolutional neural networks (LDCNNs) are vital components of mobile
intelligence, particularly in mobile vision. Although various heavy networks with increasingly …

Structured pruning is a commonly used technique in deploying deep neural networks
(DNNs) onto resource-constrained devices. However, the existing pruning methods are …

Abstract Recently, Vision Transformer (ViT) has achieved remarkable success in several
computer vision tasks. The progresses are highly relevant to the architecture design, then it …

Deep learning algorithms are increasingly employed at the edge. However, edge devices
are resource constrained and thus require efficient deployment of deep neural networks …

Artificial Intelligence (AI) has achieved significant advancements in technology and research
with the development over several decades, and is widely used in many areas including …

The existing model compression methods via structured pruning typically require
complicated multi-stage procedures. Each individual stage necessitates numerous …

We focus on addressing the dense backward propagation issue for training efficiency of N:
M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves …