Deep neural networks (DNNs) have recently achieved impressive success across a wide
range of real-world vision and language processing tasks, spanning from image …

The prohibitive complexity of convolutional neural networks (CNNs) has triggered an
increasing demand for network simplification. To this end, one natural solution is to remove …

Neural network architecture search (NAS) technology is pivotal for designing lightweight
convolutional neural networks (CNNs), facilitating the automatic search for network …

The low-cost Neural Architecture Search (NAS) for lightweight networks working on massive
mobile devices is essential for fast-developing ICT technology. Current NAS work can not …

In hardware-aware neural architecture search (NAS), accurately assessing a model's
inference efficiency is crucial for search optimization. Traditional approaches, which …

Differentiable architecture search (DARTS) yields highly efficient gradient-based neural
architecture search (NAS) by relaxing the discrete operation selection to optimize …

Neural architecture search automates the design of neural network architectures usually by
exploring a large and thus complex architecture search space. To advance the architecture …

Graph Neural Networks (GNNs) are becoming increasingly popular for graph-based
learning tasks such as point cloud processing due to their state-of-the-art (SOTA) …

DARTS search space (DSS) has become a canonical benchmark for NAS whereas some
emerging works pointed out the issue of narrow accuracy range and claimed it would hurt …

Edge devices are increasingly utilized for deploying deep learning applications on
embedded systems. The real-time nature of many applications and the limited resources of …