Edge Intelligence (EI) integrates Edge Computing (EC) and Artificial Intelligence (AI) to push
the capabilities of AI to the network edge for real-time, efficient and secure intelligent …

The increasing demand for improving deep learning model performance has led to a
paradigm shift in supporting low-precision computation to harness the robustness of deep …

Large language models (LLMs) are integral to modern natural language processing and
artificial intelligence. However, they face challenges in managing their significant memory …

Large language models (LLMs) have been widely applied but face challenges in efficient
inference. While quantization methods reduce computational demands, ultra-low bit …

The rapid growth in the parameters of large language models (LLMs) has made inference
latency a fundamental bottleneck, limiting broader application of LLMs. Speculative …

Transformer models have revolutionized AI tasks, but their large size hinders real-world
deployment on resource-constrained and latency-critical edge devices. While binarized …

This work presents a Fully BInarized Large Language Model (FBI-LLM), demonstrating for
the first time how to train a large-scale binary language model from scratch (not the partial …

As the parameter size of large language models (LLMs) continues to expand, the need for a
large memory footprint and high communication bandwidth have become significant …

Parameter quantization for Large Language Models (LLMs) has attracted increasing
attentions recently in reducing memory costs and improving computational efficiency. Early …

Binarization, which converts weight parameters to binary values, has emerged as an
effective strategy to reduce the size of large language models (LLMs). However, typical …