English
Related papers

Related papers: R2 Loss: Range Restriction Loss for Model Compress…

200 papers

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 David Qiu , David Rim , Shaojin Ding , Oleg Rybakov , Yanzhang He

Quantizing a floating-point neural network to its fixed-point representation is crucial for Learned Image Compression (LIC) because it improves decoding consistency for interoperability and reduces space-time complexity for implementation.…

Image and Video Processing · Electrical Eng. & Systems 2023-10-10 Junqi Shi , Ming Lu , Zhan Ma

Based on the model's resilience to computational noise, model quantization is important for compressing models and improving computing speed. Existing quantization techniques rely heavily on experience and "fine-tuning" skills. In the…

Machine Learning · Computer Science 2022-07-22 Daning Cheng , Wenguang Chen

Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Ping Xue , Yang Lu , Jingfei Chang , Xing Wei , Zhen Wei

Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent…

Machine Learning · Computer Science 2018-02-02 Chen Xu , Jianqiang Yao , Zhouchen Lin , Wenwu Ou , Yuanbin Cao , Zhirong Wang , Hongbin Zha

Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs.…

Computation and Language · Computer Science 2024-12-02 Yuzhuang Xu , Xu Han , Zonghan Yang , Shuo Wang , Qingfu Zhu , Zhiyuan Liu , Weidong Liu , Wanxiang Che

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

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Chen Tang , Yuan Meng , Jiacheng Jiang , Shuzhao Xie , Rongwei Lu , Xinzhu Ma , Zhi Wang , Wenwu Zhu

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant…

Machine Learning · Computer Science 2020-12-15 Itay Hubara , Yury Nahshan , Yair Hanani , Ron Banner , Daniel Soudry

At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the…

Machine Learning · Computer Science 2022-07-08 Huabin Diao , Gongyan Li , Shaoyun Xu , Yuexing Hao

Low-bit quantization is widely used to compress super-resolution (SR) models and reduce storage and computation costs for deployment on resource-limited devices. However, when SR models are pushed to ultra-low precision (2-4 bits),…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Haotong Qin , Xudong Ma , Xianglong Liu , Jie Luo , Jinyang Guo , Michele Magno , Yulun Zhang

Large Language Models (LLMs) deliver strong performance across a wide range of NLP tasks, but their massive sizes hinder deployment on resource-constrained devices. To reduce their computational and memory burden, various compression…

Machine Learning · Computer Science 2026-05-18 Dung Anh Hoang , Cuong Pham , Cuong Nguyen , Trung le , Jianfei Cai , Thanh-Toan Do

Reducing bit-widths of activations and weights of deep networks makes it efficient to compute and store them in memory, which is crucial in their deployments to resource-limited devices, such as mobile phones. However, decreasing bit-widths…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Sangil Jung , Changyong Son , Seohyung Lee , Jinwoo Son , Youngjun Kwak , Jae-Joon Han , Sung Ju Hwang , Changkyu Choi

Deep neural networks have been proven effective in a wide range of tasks. However, their high computational and memory costs make them impractical to deploy on resource-constrained devices. To address this issue, quantization schemes have…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Jie Hu , Mengze Zeng , Enhua Wu

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…

Computation and Language · Computer Science 2025-02-27 Liangdong Liu , Zhitong Zheng , Cong Wang , Tianhuang Su , Zhenyu Yang

Deep learning models have shown strong performance in medical image analysis, but deploying them in low-resource clinical environments remains difficult due to computational, memory, and power constraints. This paper presents a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Sumanth Meenan Kanneti , Aryan Shah

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

Computation and Language · Computer Science 2025-02-24 Weilan Wang , Yu Mao , Dongdong Tang , Hongchao Du , Nan Guan , Chun Jason Xue

Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization enables hardware-friendly, matmul-free inference by stacking…

Artificial Intelligence · Computer Science 2026-05-19 Youngcheon You , Banseok Lee , Minseop Choi , Seonyoung Kim , Hyochan Chong , Changdong Kim , Youngmin Kim , Dongkyu Kim

As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization methods, such as GPTQ, have made progress in achieving…

Machine Learning · Computer Science 2023-12-14 Liang Li , Qingyuan Li , Bo Zhang , Xiangxiang Chu

Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, a post-training…

Computation and Language · Computer Science 2026-05-19 Wenhua Cheng , Weiwei Zhang , Heng Guo , Haihao Shen , Zaner Ma

Quantization techniques commonly reduce the inference costs of neural networks by restricting the precision of weights and activations. Recent studies show that also reducing the precision of the accumulator can further improve hardware…

Machine Learning · Computer Science 2024-01-22 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig , Yaman Umuroglu