English
Related papers

Related papers: Preserve-Then-Quantize: Balancing Rank Budgets for…

200 papers

Vector Quantization (VQ) is an appealing model compression method to obtain a tiny model with less accuracy loss. While methods to obtain better codebooks and codes under fixed clustering dimensionality have been extensively studied,…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Zezhou Zhu , Yucong Zhou , Zhao Zhong

Post-training quantization of Large Language Models (LLMs) has proven effective in reducing the memory and computational requirements for inference. In this study, we focus on a straightforward question: When aiming for a target accuracy or…

Computation and Language · Computer Science 2025-08-08 Zeyu Cao , Boyang Gu , Cheng Zhang , Pedro Gimenes , Jianqiao Lu , Jianyi Cheng , Xitong Gao , Yiren Zhao

In this paper, we present a simple optimization-based preprocessing technique called Weight Magnitude Reduction (MagR) to improve the performance of post-training quantization. For each linear layer, we adjust the pre-trained floating-point…

Machine Learning · Computer Science 2024-10-18 Aozhong Zhang , Naigang Wang , Yanxia Deng , Xin Li , Zi Yang , Penghang Yin

Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking neural networks (SNNs) share the goal of enhancing…

Neural and Evolutionary Computing · Computer Science 2024-05-01 Sreyes Venkatesh , Razvan Marinescu , Jason K. Eshraghian

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Pierre Stock , Armand Joulin , Rémi Gribonval , Benjamin Graham , Hervé Jégou

We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full-precision and weight-quantized…

Machine Learning · Computer Science 2023-09-12 Xidan Song , Youcheng Sun , Mustafa A. Mustafa , Lucas C. Cordeiro

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

At very high sparsity, neural network pruning does more than decide which weights remain. It also determines where pruning induced damage is placed across the network, and whether that damage can be recovered by a fixed lightweight repair…

Machine Learning · Computer Science 2026-05-26 Qishi Zhan , Liang He , Minxuan Hu , Ziheng Chen

RWKV is a modern RNN architecture with comparable performance to Transformer, but still faces challenges when deployed to resource-constrained devices. Post Training Quantization (PTQ), which is a an essential technique to reduce model size…

Machine Learning · Computer Science 2025-05-08 Chen Xu , Yuxuan Yue , Zukang Xu , Xing Hu , Jiangyong Yu , Zhixuan Chen , Sifan Zhou , Zhihang Yuan , Dawei Yang

We study the challenging task of neural network quantization without end-to-end retraining, called Post-training Quantization (PTQ). PTQ usually requires a small subset of training data but produces less powerful quantized models than…

Machine Learning · Computer Science 2021-07-27 Yuhang Li , Ruihao Gong , Xu Tan , Yang Yang , Peng Hu , Qi Zhang , Fengwei Yu , Wei Wang , Shi Gu

Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden state of trained linear attention models often exhibits a low-rank structure,…

Machine Learning · Computer Science 2026-02-13 Philipp Nazari , T. Konstantin Rusch

This paper presents an optimized methodology to design and deploy Speech Enhancement (SE) algorithms based on Recurrent Neural Networks (RNNs) on a state-of-the-art MicroController Unit (MCU), with 1+8 general-purpose RISC-V cores. To…

Sound · Computer Science 2022-10-17 Manuele Rusci , Marco Fariselli , Martin Croome , Francesco Paci , Eric Flamand

Quantization-aware training (QAT) is an effective method to drastically reduce the memory footprint of LLMs while keeping performance degradation at an acceptable level. However, the optimal choice of quantization format and bit-width…

Machine Learning · Computer Science 2026-02-18 Sohir Maskey , Constantin Eichenberg , Johannes Messner , Douglas Orr

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…

Machine Learning · Computer Science 2023-09-21 Jinjie Zhang , Rayan Saab

With the advent of large language models (LLMs), numerous Post-Training Quantization (PTQ) strategies have been proposed to alleviate deployment barriers created by their enormous parameter counts. Quantization achieves compression by…

Machine Learning · Computer Science 2025-09-24 Wonjun Bang , Jongseok Park , Hongseung Yu , Kyungmin Bin , Kyunghan Lee

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Zhihang Yuan , Yiqi Chen , Chenhao Xue , Chenguang Zhang , Qiankun Wang , Guangyu Sun

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…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Dawei Yang , Ning He , Xing Hu , Zhihang Yuan , Jiangyong Yu , Chen Xu , Zhe Jiang

Neural image compression has been shown to outperform traditional image codecs in terms of rate-distortion performance. However, quantization introduces errors in the compression process, which can degrade the quality of the compressed…

Machine Learning · Computer Science 2024-03-27 Wei Luo , Bo Chen

We consider the problem of model compression for Large Language Models (LLMs) at post-training time, where the task is to compress a well-trained model using only a small set of calibration input data. In this work, we introduce a new…

Machine Learning · Statistics 2024-12-12 Meyer Scetbon , James Hensman

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao
‹ Prev 1 3 4 5 6 7 10 Next ›