English
Related papers

Related papers: TensorGPT: Efficient Compression of Large Language…

200 papers

The rise of large language models (LLMs) is revolutionizing information retrieval, question answering, summarization, and code generation tasks. However, in addition to confidently presenting factually inaccurate information at times (known…

Artificial Intelligence · Computer Science 2023-04-26 Henry Gilbert , Michael Sandborn , Douglas C. Schmidt , Jesse Spencer-Smith , Jules White

Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank…

Computation and Language · Computer Science 2026-02-09 Jiayi Tian , Ryan Solgi , Jinming Lu , Yifan Yang , Hai Li , Zheng Zhang

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Computation and Language · Computer Science 2026-04-17 Andrew Kiruluta

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face…

Computation and Language · Computer Science 2025-02-19 Pengxiang Lan , Haoyu Xu , Enneng Yang , Yuliang Liang , Guibing Guo , Jianzhe Zhao , Xingwei Wang

Tensor decomposition is a mathematically supported technique for data compression. It consists of applying some kind of a Low Rank Decomposition technique on the tensors or matrices in order to reduce the redundancy of the data. However, it…

Machine Learning · Computer Science 2025-05-27 Habib Hajimolahoseini , Walid Ahmed , Austin Wen , Yang Liu

Many real-world datasets are represented as tensors, i.e., multi-dimensional arrays of numerical values. Storing them without compression often requires substantial space, which grows exponentially with the order. While many tensor…

Machine Learning · Computer Science 2023-09-21 Taehyung Kwon , Jihoon Ko , Jinhong Jung , Kijung Shin

We introduce TQCompressor, a novel method for neural network model compression with improved tensor decompositions. We explore the challenges posed by the computational and storage demands of pre-trained language models in NLP tasks and…

Machine Learning · Computer Science 2024-01-30 V. Abronin , A. Naumov , D. Mazur , D. Bystrov , K. Tsarova , Ar. Melnikov , I. Oseledets , S. Dolgov , R. Brasher , M. Perelshtein

This paper introduces a novel method of Progressive Low Rank Decomposition (PLRD) tailored for the compression of large language models. Our approach leverages a pre-trained model, which is then incrementally decompressed to smaller sizes…

Computation and Language · Computer Science 2024-07-01 Habib Hajimolahoseini , Mohammad Hassanpour , Foozhan Ataiefard , Boxing Chen , Yang Liu

Prompt Tuning (PT) enables the adaptation of Pre-trained Large Language Models (PLMs) to downstream tasks by optimizing a small amount of soft virtual tokens, which are prepended to the input token embeddings. Recently, Decomposed Prompt…

Computation and Language · Computer Science 2025-12-23 Pengwei Tang , Xiaolin Hu , Yong Liu

The increasing size of generative Pre-trained Language Models (PLMs) has greatly increased the demand for model compression. Despite various methods to compress BERT or its variants, there are few attempts to compress generative PLMs, and…

Computation and Language · Computer Science 2022-07-19 Chaofan Tao , Lu Hou , Wei Zhang , Lifeng Shang , Xin Jiang , Qun Liu , Ping Luo , Ngai Wong

Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…

Machine Learning · Computer Science 2025-12-17 Sidhant Sundrani , Francesco Tudisco , Pasquale Minervini

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

Computation and Language · Computer Science 2024-02-16 Wenxiao Wang , Wei Chen , Yicong Luo , Yongliu Long , Zhengkai Lin , Liye Zhang , Binbin Lin , Deng Cai , Xiaofei He

We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permits taking computational shortcuts when computing mappings.…

Machine Learning · Computer Science 2021-07-15 Anton Obukhov , Maxim Rakhuba , Alexander Liniger , Zhiwu Huang , Stamatios Georgoulis , Dengxin Dai , Luc Van Gool

GPT is an auto-regressive Transformer-based pre-trained language model which has attracted a lot of attention in the natural language processing (NLP) domain due to its state-of-the-art performance in several downstream tasks. The success…

Computation and Language · Computer Science 2021-10-18 Ali Edalati , Marzieh Tahaei , Ahmad Rashid , Vahid Partovi Nia , James J. Clark , Mehdi Rezagholizadeh

The demand for deploying large language models(LLMs) on mobile devices continues to increase, driven by escalating data security concerns and cloud costs. However, network bandwidth and memory limitations pose challenges for deploying…

Machine Learning · Computer Science 2024-07-02 Songwei Liu , Chao Zeng , Lianqiang Li , Chenqian Yan , Lean Fu , Xing Mei , Fangmin Chen

Transformer-based language models achieve strong performance across NLP tasks, but their quadratic parameter scaling with hidden dimension makes deployment on resource-constrained hardware expensive. We study Matrix Product Operator (MPO)…

Computation and Language · Computer Science 2026-03-31 Younes Javanmard , Tanmoy Pandit , Masoud Mardani

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Modern deep neural networks (DNNs) are extremely powerful; however, this comes at the price of increased depth and having more parameters per layer, making their training and inference more computationally challenging. In an attempt to…

Machine Learning · Statistics 2024-03-04 Lingyu Gu , Yongqi Du , Yuan Zhang , Di Xie , Shiliang Pu , Robert C. Qiu , Zhenyu Liao

This paper describes a new method for representing embedding tables of graph neural networks (GNNs) more compactly via tensor-train (TT) decomposition. We consider the scenario where (a) the graph data that lack node features, thereby…

Machine Learning · Computer Science 2022-06-22 Chunxing Yin , Da Zheng , Israt Nisa , Christos Faloutos , George Karypis , Richard Vuduc