Related papers: BiTAT: Neural Network Binarization with Task-depen…

We propose Additive Powers-of-Two~(APoT) quantization, an efficient non-uniform quantization scheme for the bell-shaped and long-tailed distribution of weights and activations in neural networks. By constraining all quantization levels as…

Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources. Network quantization is a powerful technique to compress neural networks, allowing for more…

As the applications of deep learning models on edge devices increase at an accelerating pace, fast adaptation to various scenarios with varying resource constraints has become a crucial aspect of model deployment. As a result, model…

Neural networks are getting deeper and more computation-intensive nowadays. Quantization is a useful technique in deploying neural networks on hardware platforms and saving computation costs with negligible performance loss. However, recent…

Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for INT4 (or lower) but provide reasonable accuracy for INT8 (or…

Deploying neural networks on the edge has become increasingly important as deep learning is being applied in an increasing amount of applications. At the edge computing hardware typically has limited resources disallowing to run neural…

Network quantization generally converts full-precision weights and/or activations into low-bit fixed-point values in order to accelerate an inference process. Recent approaches to network quantization further discretize the gradients into…

Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a…

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word…

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs) have been significant. While demonstrating high accuracy, DNNs are associated with a huge number of parameters and computations, which leads to high memory…

Large language models (LLMs) have wide applications in the field of natural language processing(NLP), such as GPT-4 and Llama. However, with the exponential growth of model parameter sizes, LLMs bring significant resource overheads. Low-bit…

As wireless communication systems advance toward Sixth Generation (6G) Radio Access Networks (RAN), Deep Learning (DL)-based neural receivers are emerging as transformative solutions for Physical Layer (PHY) processing, delivering superior…

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

1 bit deep neural networks (DNNs), of which both the activations and weights are binarized , are attracting more and more attention due to their high computational efficiency and low memory requirement . However, the drawback of large…

With unprecedented rapid development, deep neural networks (DNNs) have deeply influenced almost all fields. However, their heavy computation costs and model sizes are usually unacceptable in real-world deployment. Model quantization, an…

Post-training quantization is a key technique for reducing the memory and inference latency of large language models by quantizing weights and activations without requiring retraining. However, existing methods either (1) fail to account…

Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. However, existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths,…

Post-training quantization for reducing the storage of deep neural network models has been demonstrated to be an effective way in various tasks. However, low-bit quantization while maintaining model accuracy is a challenging problem. In…

INT8 quantization has become one of the standard techniques for deploying convolutional neural networks (CNNs) on edge devices to reduce the memory and computational resource usages. By analyzing quantized performances of existing…