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

The deployment of Large Language Models (LLMs) on edge devices is increasingly
important to enhance on-device intelligence. Weight quantization is crucial for reducing the …

On-device adapting to continual, unpredictable domain shifts is essential for mobile
applications like autonomous driving and augmented reality to deliver seamless user …

In this work we show that the size versus accuracy trade-off of neural network quantization
can be significantly improved by increasing the quantization dimensionality. We propose the …

Web applications have increasingly adopted Deep Learning (DL) through in-browser
inference, wherein DL inference performs directly within Web browsers. The actual …

In this paper, a table lookup-based computing technique is proposed to perform
convolutional neural network (CNN) inference without multiplication, and its FPGA …

Modern speech understanding (SU) runs a sophisticated pipeline: ingesting streaming voice
input, the pipeline executes encoder-decoder based deep neural networks repeatedly; by …

DRAM-based processing-in-memory (DRAM-PIM) has gained commercial prominence in
recent years. However, their integration for deep learning acceleration poses inherent …

The emergence of neural network capabilities invariably leads to a significant surge in
computational demands due to expanding model sizes and increased computational …

Large Language Models (LLMs), based on transformer architecture, have demonstrated
remarkable capabilities in natural language processing tasks, enabling machines to …