English
Related papers

Related papers: BWTA: Accurate and Efficient Binarized Transformer…

200 papers

Bit-level sparsity methods skip ineffectual zero-bit operations and are typically applicable within bit-serial deep learning accelerators. This type of sparsity at the bit-level is especially interesting because it is both orthogonal and…

Machine Learning · Computer Science 2024-09-10 Yuzong Chen , Jian Meng , Jae-sun Seo , Mohamed S. Abdelfattah

This paper explores a novel paradigm in low-bit (i.e. 4-bits or lower) quantization, differing from existing state-of-the-art methods, by framing optimal quantization as an architecture search problem within convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Róisín Luo , Alexandru Drimbarean , James McDermott , Colm O'Riordan

Neural network hardware is considered an essential part of future edge devices. In this paper, we propose a binary-weight spiking neural network (BW-SNN) hardware architecture for low-power real-time object classification on edge platforms.…

Signal Processing · Electrical Eng. & Systems 2020-03-16 Pai-Yu Tan , Po-Yao Chuang , Yen-Ting Lin , Cheng-Wen Wu , Juin-Ming Lu

Arbitrary bit-width network quantization has received significant attention due to its high adaptability to various bit-width requirements during runtime. However, in this paper, we investigate existing methods and observe a significant…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Yunshan Zhong , Yuyao Zhou , Fei Chao , Rongrong Ji

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time. At training-time the binary weights and activations are used for computing the parameters gradients. During…

Machine Learning · Computer Science 2016-03-18 Matthieu Courbariaux , Itay Hubara , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio

Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to efficiently compress models to binary (1-bit) levels, as they either require large amounts of…

Machine Learning · Computer Science 2026-05-19 Hyochan Chong , Dongkyu Kim , Changdong Kim , Minseop Choi

We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wise reconstruction methods, we jointly optimize over the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Shile Li , Markus Karmann , Onay Urfalioglu

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

We present PrecisionBatching, a quantized inference algorithm for speeding up neural network execution on traditional hardware platforms at low bitwidths without the need for retraining or recalibration. PrecisionBatching decomposes a…

Machine Learning · Computer Science 2020-03-03 Maximilian Lam , Zachary Yedidia , Colby Banbury , Vijay Janapa Reddi

We present an overview of techniques for quantizing convolutional neural networks for inference with integer weights and activations. Per-channel quantization of weights and per-layer quantization of activations to 8-bits of precision…

Machine Learning · Computer Science 2018-06-22 Raghuraman Krishnamoorthi

Network quantization is arguably one of the most practical network compression approaches for reducing the enormous resource consumption of modern deep neural networks. They usually require diverse and subtle design choices for specific…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Ningyuan Tang , Minghao Fu , Hao Yu , Jianxin Wu

Bit-serial architectures can handle Neural Networks (NNs) with different weight precisions, achieving higher resource efficiency compared with bit-parallel architectures. Besides, the weights contain abundant zero bits owing to the fault…

Hardware Architecture · Computer Science 2023-02-02 Wenhao Sun , Zhiwei Zou , Deng Liu , Wendi Sun , Song Chen , Yi Kang

Long Short-Term Memory (LSTM) and 3D convolution (Conv3D) show impressive results for many video-based applications but require large memory and intensive computing. Motivated by recent works on hardware-algorithmic co-design towards…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Van Thien Nguyen , William Guicquero , Gilles Sicard

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

Machine Learning · Computer Science 2025-10-13 Kaiyan Zhao , Tsuguchika Tabaru , Kenichi Kobayashi , Takumi Honda , Masafumi Yamazaki , Yoshimasa Tsuruoka

Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly…

Robotics · Computer Science 2024-12-03 Seongmin Park , Hyungmin Kim , Wonseok Jeon , Juyoung Yang , Byeongwook Jeon , Yoonseon Oh , Jungwook Choi

Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision floating point counterparts. The most extreme quantization…

Machine Learning · Computer Science 2021-11-09 Yaniv Shulman

The deployment of large language models (LLMs) is increasingly constrained by memory and latency bottlenecks, motivating the need for quantization techniques that flexibly balance accuracy and efficiency. Recent work has introduced…

Machine Learning · Computer Science 2026-02-03 Gunho Park , Jeongin Bae , Beomseok Kwon , Byeongwook Kim , Se Jung Kwon , Dongsoo Lee

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but…

Machine Learning · Computer Science 2024-08-22 Elias Frantar , Roberto L. Castro , Jiale Chen , Torsten Hoefler , Dan Alistarh

Kernel approximation is widely used to scale up kernel SVM training and prediction. However, the memory and computation costs of kernel approximation models are still too high if we want to deploy them on memory-limited devices such as…

Machine Learning · Computer Science 2020-10-07 Zijian Lei , Liang Lan

We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance. QLoRA backpropagates gradients through a…

Machine Learning · Computer Science 2023-05-24 Tim Dettmers , Artidoro Pagnoni , Ari Holtzman , Luke Zettlemoyer