Large language models (LLMs) have revolutionized natural language processing with their
exceptional capabilities. However, deploying LLMs on resource-constrained edge devices …

As machine learning and AI continue to rapidly develop, and with the ever-closer end of
Moore's law, new avenues and novel ideas in architecture design are being created and …

After the success of the transformer networks on natural language processing (NLP), the
application of transformers to computer vision (CV) has followed suit to deliver …

The attention mechanisms of transformers effectively extract pertinent information from the
input sequence. However, the quadratic complexity of self-attention incurs heavy …

Quantization is one of the most hardware-efficient ways to reduce inference costs for deep
neural network (DNN) models. Nevertheless, with the continuous increase of DNN model …

Self-attention networks such as Transformer have become state-of-the-art models for natural
language processing (NLP) problems. Softmax function, which serves as a normalizer to …

After the success of the transformer networks on natural language processing (NLP), the
application of transformers to computer vision has followed suit to deliver unprecedented …

Attention-based models, such as transformers, have achieved remarkable success across
various tasks. However, their deployment is hindered by challenges such as high memory …

All-in-one image restoration (IR) recovers images from various unknown distortions by a
single model, such as rain, haze, and blur. Transformer-based IR methods have significantly …

Vision Transformers (ViTs) have achieved remarkable success across various tasks.
However, their deployment is hindered by challenges such as high memory requirements …