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 …

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 …

Adapters are a parameter-efficient alternative to fine-tuning, which augment a frozen base
network to learn new tasks. Yet, the inference of the adapted model is often slower than the …

The leap in performance in state-of-the-art computer vision methods is attributed to the
development of deep neural networks. However it often comes at a computational price …

The growing interest in the Internet of Things (IoT) and mobile artificial intelligence
applications is pushing the investigation on deep neural networks (DNNs) that can operate …

Convolutional neural networks (CNNs) play a crucial role and achieve top results in
computer vision tasks but at the cost of high computational cost and storage complexity. One …

The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a
highly sparse subnetwork (ie, winning tickets) that can achieve even better performance …

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different
subnetworks, ie, experts, through trainable routers. MoE reduces the training computation …

Network pruning and knowledge distillation, as two effective network compression
techniques, have drawn extensive attention due to their success in reducing model …