English
Related papers

Related papers: The Fourth State: Signed-Zero Ternary for Stable L…

200 papers

Large language models (LLMs) have achieved remarkable performance on Natural Language Processing (NLP) tasks, but they are hindered by high computational costs and memory requirements. Ternarization, an extreme form of quantization, offers…

Machine Learning · Computer Science 2024-06-12 Tianqi Chen , Zhe Li , Weixiang Xu , Zeyu Zhu , Dong Li , Lu Tian , Emad Barsoum , Peisong Wang , Jian Cheng

One of the possible representations of three-valued instantaneous noise-based logic is proposed. The third value is an uncertain bit value, which can be useful in artificial intelligence applications. There is a forth value, too, that can…

Emerging Technologies · Computer Science 2023-05-10 Laszlo B. Kish

Quantization is widely applied in machine learning to reduce computational and storage costs for both data and models. Considering that classification tasks are fundamental to the field, it is crucial to investigate how quantization impacts…

Machine Learning · Computer Science 2025-07-14 Weizhi Lu , Mingrui Chen , Weiyu Li

Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Weixiang Xu , Xiangyu He , Tianli Zhao , Qinghao Hu , Peisong Wang , Jian Cheng

We introduce the concept of selective quantum state tomography or SQST, a tomographic scheme that enables a user to estimate arbitrary elements of an unknown quantum state using a fixed measurement record. We demonstrate how this may be…

Quantum Physics · Physics 2020-06-12 Joshua Morris , Borivoje Dakić

The deployment of Large Language Models (LLMs) on resource-constrained edge devices is increasingly hindered by prohibitive memory and computational requirements. While ternary quantization offers a compelling solution by reducing weights…

Machine Learning · Computer Science 2026-01-14 Hong Huang , Decheng Wu , Qiangqiang Hu , Guanghua Yu , Jinhai Yang , Jianchen Zhu , Xue Liu , Dapeng Wu

Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements. Weight-only quantization has emerged as…

Computation and Language · Computer Science 2024-10-10 Wenhua Cheng , Weiwei Zhang , Haihao Shen , Yiyang Cai , Xin He , Kaokao Lv , Yi Liu

Quantization of neural networks provides benefits of inference in less compute and memory requirements. Previous work in quantization lack two important aspects which this work provides. First almost all previous work in quantization used a…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Zia Badar

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

Inference time, model size, and accuracy are critical for deploying deep neural network models. Numerous research efforts have been made to compress neural network models with faster inference and higher accuracy. Pruning and quantization…

Machine Learning · Computer Science 2023-03-06 Dan Liu , Xue Liu

Training quantized neural networks requires addressing the non-differentiable and discrete nature of the underlying optimization problem. To tackle this challenge, the straight-through estimator (STE) has become the most widely adopted…

Machine Learning · Computer Science 2025-05-26 Halyun Jeong , Jack Xin , Penghang Yin

To address the communication bottleneck challenge in distributed learning, our work introduces a novel two-stage quantization strategy designed to enhance the communication efficiency of distributed Stochastic Gradient Descent (SGD). The…

Machine Learning · Computer Science 2024-02-05 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Congduan Li , Linqi Song

Neural network models are resource hungry. It is difficult to deploy such deep networks on devices with limited resources, like smart wearables, cellphones, drones, and autonomous vehicles. Low bit quantization such as binary and ternary…

Machine Learning · Computer Science 2021-09-15 Ryan Razani , Grégoire Morin , Vahid Partovi Nia , Eyyüb Sari

Quantum state tomography (QST) is a fundamental technique for estimating the state of a quantum system from measured data and plays a crucial role in evaluating the performance of quantum devices. However, standard estimation methods become…

Quantum Physics · Physics 2026-01-27 Shakir Showkat Sofi , Charlotte Vermeylen , Lieven De Lathauwer

Canonical LST (sTEZ) is an enshrined, protocol-native mechanism designed to mitigate the centralization risks associated with liquid staking intermediaries. Intended to complement direct staking rather than replace it, Canonical LST…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-05 Mathias Bourgoin , Arthur Breitman , Pierrick Couderc , Zaynah Dargaye , Diane Gallois-Wong , Marina Polubelova , Lucas Randazzo , Julien Tesson

Ternary Neural Networks (TNNs) have received much attention due to being potentially orders of magnitude faster in inference, as well as more power efficient, than full-precision counterparts. However, 2 bits are required to encode the…

Machine Learning · Computer Science 2021-07-30 Peng Chen , Bohan Zhuang , Chunhua Shen

It is shown that, despite strong nonlinearity, entanglement of formation of two-qubit state can be measured without prior state reconstruction. Collective measurements on small number of copies are provided that allow to determine quantum…

Quantum Physics · Physics 2007-05-23 Pawel Horodecki

We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers. Existing methods for quantizing models either modify the training procedure,or they require an…

Computation and Language · Computer Science 2022-11-18 Yousef El-Kurdi , Jerry Quinn , Avirup Sil

A state-of-the-art strategy for digitally representing a bandlimited signal $f$ is $\Sigma\Delta$ quantization. $\Sigma\Delta$ quantization schemes choose a bit sequence $(q_n)$ representing the samples $(y_n)$ of $f$ sequentially based on…

Information Theory · Computer Science 2026-05-19 Rohan Joy , Felix Krahmer , Alessandro Lupoli

Despite the achievements of recent binarization methods on reducing the performance degradation of Binary Neural Networks (BNNs), gradient mismatching caused by the Straight-Through-Estimator (STE) still dominates quantized networks. This…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Junjie Liu , Dongchao Wen , Deyu Wang , Wei Tao , Tse-Wei Chen , Kinya Osa , Masami Kato
‹ Prev 1 2 3 10 Next ›