Artificial intelligence technologies based on deep convolutional neural networks and large
language models have made significant breakthroughs in many tasks, such as image …

Automated machine learning (AutoML) has achieved remarkable success in automating the
non-trivial process of designing machine learning models. Among the focal areas of AutoML …

Quantization is of significance for compressing the over-parameterized deep neural models
and deploying them on resource-limited devices. Fixed-precision quantization suffers from …

Despite the outstanding performance of transformers in both language and vision tasks, the
expanding computation and model size have increased the demand for efficient …

Abstract Model quantization is widely used to realize the promise of ubiquitous embedded
deep network inference. While mixed-precision quantization has shown promising …

Diffusion models have emerged as preeminent contenders in the realm of generative
models. Distinguished by their distinctive sequential generative processes, characterized by …

Network quantization, which strives to reduce the precision of model parameters and/or
features, is one of the most efficient ways to accelerate model inference and reduce memory …

Quantization is a promising technique for reducing the bit-width of deep models to improve
their runtime performance and storage efficiency, and thus becomes a fundamental step for …

Embedding techniques have become essential components of large databases in the deep
learning era. By encoding discrete entities, such as words, items, or graph nodes, into …

Quantization is commonly used to reduce the inference time of convolutional neural
networks (CNNs). To reduce the inference time without drastically reducing accuracy …