English
Related papers

Related papers: Influence-Inspired Spectral Rotations for Extreme …

200 papers

Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly matched to a low-bit…

Machine Learning · Computer Science 2026-05-27 Ke Li , Dong An , Xiaoling Zang , Can Ye , Liang Xie , Qibo Qiu , Chen Shen , Xiaofei He , Wenxiao Wang

Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs). Recently,…

Computation and Language · Computer Science 2024-09-30 Xijie Huang , Zechun Liu , Shih-Yang Liu , Kwang-Ting Cheng

Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization…

Machine Learning · Computer Science 2026-04-22 Siqing Song , Chuang Wang , Yong Lang , Yi Yang , Xu-Yao Zhang

The accurate recovery of constituent-level optical properties from integrating sphere measurements is a central analytical challenge in pharmaceutical analysis, food science, and biomedical diagnostics. Neural network autoencoders can…

Optics · Physics 2026-05-13 Martin Hohmann

The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind. We identify…

Computation and Language · Computer Science 2023-12-12 Yichi Zhang , Ankush Garg , Yuan Cao , Łukasz Lew , Behrooz Ghorbani , Zhiru Zhang , Orhan Firat

Quantization effectively reduces the serving costs of Large Language Models (LLMs) by speeding up data movement through compressed parameters and enabling faster operations via integer arithmetic. However, activating integer arithmetic…

Machine Learning · Computer Science 2025-06-04 Patrik Czakó , Gábor Kertész , Sándor Szénási

A new iterative low complexity algorithm has been presented for computing the Walsh-Hadamard transform (WHT) of an $N$ dimensional signal with a $K$-sparse WHT, where $N$ is a power of two and $K = O(N^\alpha)$, scales sub-linearly in $N$…

Information Theory · Computer Science 2019-05-08 Robin Scheibler , Saeid Haghighatshoar , Martin Vetterli

Large-scale foundation models have demonstrated remarkable versatility across a wide range of downstream tasks. However, fully fine-tuning these models incurs prohibitive computational costs, motivating the development of…

Machine Learning · Computer Science 2025-05-30 Chongjie Si , Xuankun Yang , Muqing Liu , Yadao Wang , Xiaokang Yang , Wenbo Su , Bo Zheng , Wei Shen

Modeling the large-scale structure of the universe on nonlinear scales has the potential to substantially increase the science return of upcoming surveys by increasing the number of modes available for model comparisons. One way to achieve…

Cosmology and Nongalactic Astrophysics · Physics 2016-11-30 Marcel Schmittfull , Zvonimir Vlah

Despite the outstanding performance of transformers in both language and vision tasks, the expanding computation and model size have increased the demand for efficient deployment. To address the heavy computation and parameter drawbacks,…

Machine Learning · Computer Science 2024-10-15 Xijie Huang , Zhiqiang Shen , Pingcheng Dong , Kwang-Ting Cheng

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

Standard Transformers impose near-exponential decay on the influence of distant tokens, conflicting with the power-law structure of long-range dependencies in natural language. We introduce the \emph{Variable-Order Retention Transformer}…

Machine Learning · Computer Science 2026-05-12 Nabil Mlaiki

The two point angular correlation function is an excellent measure of structure in the universe. To extract from it the three dimensional power spectrum, one must invert Limber's Equation. Here we perform this inversion using a Bayesian…

Astrophysics · Physics 2008-11-26 Scott Dodelson , Enrique Gaztanaga

This paper investigates the power control problem in wireless networks by repurposing pre-trained large language models (LLMs) as relational reasoning backbones. In hyper-connected interference environments, traditional optimization methods…

Information Theory · Computer Science 2026-04-03 Jiacheng Wang , Yucheng Sheng , Le Liang , Hao Ye , Shi Jin

Neural network quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation, while preserving the performance of the original…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Geon Park , Jaehong Yoon , Haiyang Zhang , Xing Zhang , Sung Ju Hwang , Yonina C. Eldar

Large language models (LLMs) have significantly advanced natural language processing, but their massive parameter counts create substantial computational and memory challenges during deployment. Post-training quantization (PTQ) has emerged…

Machine Learning · Computer Science 2025-11-25 Cuong Pham , Hoang Anh Dung , Cuong C. Nguyen , Trung Le , Gustavo Carneiro , Thanh-Toan Do

Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Junghwan Park , Woojin Cho , Junhyuk Heo , Darongsae Kwon , Kookjin Lee

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

We introduce ReALLM, a novel approach for compression and memory-efficient adaptation of pre-trained language models that encompasses most of the post-training quantization and fine-tuning methods for a budget of <4 bits. Pre-trained…

Machine Learning · Computer Science 2024-05-24 Louis Leconte , Lisa Bedin , Van Minh Nguyen , Eric Moulines

We study the bispectrum in Lagrangian perturbation theory. Extending past results for the power spectrum, we describe a method to efficiently compute the bispectrum in LPT, focusing on the Zeldovich approximation, in which contributions due…

Cosmology and Nongalactic Astrophysics · Physics 2024-10-07 Shi-Fan Chen , Zvonimir Vlah , Martin White