English
Related papers

Related papers: Kronecker Decomposition for GPT Compression

200 papers

In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either update all model…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Xuehai He , Chunyuan Li , Pengchuan Zhang , Jianwei Yang , Xin Eric Wang

In this paper, we combine two-step knowledge distillation, structured pruning, truncation, and vocabulary trimming for extremely compressing multilingual encoder-only language models for low-resource languages. Our novel approach…

Computation and Language · Computer Science 2025-11-07 Daniil Gurgurov , Michal Gregor , Josef van Genabith , Simon Ostermann

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

Model compression aims to deploy deep neural networks (DNN) on mobile devices with limited computing and storage resources. However, most of the existing model compression methods rely on manually defined rules, which require domain…

Computer Vision and Pattern Recognition · Computer Science 2021-11-10 Sixing Yu , Arya Mazaheri , Ali Jannesari

In Natural Language Processing (NLP), Transformers have already revolutionized the field by utilizing an attention-based encoder-decoder model. Recently, some pioneering works have employed Transformer-like architectures in Computer Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Gousia Habib , Tausifa Jan Saleem , Brejesh Lall

Large pre-trained Transformer models achieve state-of-the-art results across diverse language and reasoning tasks, but full fine-tuning incurs substantial storage, memory, and computational overhead. Parameter-efficient fine-tuning (PEFT)…

Machine Learning · Computer Science 2025-06-19 Yee Hin Chong , Peng Qu

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

Computation and Language · Computer Science 2019-04-09 Artem M. Grachev , Dmitry I. Ignatov , Andrey V. Savchenko

In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia. However, the large model size and high run-time latency are serious impediments to applying them in…

Computation and Language · Computer Science 2022-07-13 Chengqiang Lu , Jianwei Zhang , Yunfei Chu , Zhengyu Chen , Jingren Zhou , Fei Wu , Haiqing Chen , Hongxia Yang

Feature transformation plays a critical role in enhancing machine learning model performance by optimizing data representations. Recent state-of-the-art approaches address this task as a continuous embedding optimization problem, converting…

Machine Learning · Computer Science 2025-08-29 Yang Gao , Dongjie Wang , Scott Piersall , Ye Zhang , Liqiang Wang

Large generative language models have been very successful for English, but other languages lag behind, in part due to data and computational limitations. We propose a method that may overcome these problems by adapting existing pre-trained…

Computation and Language · Computer Science 2021-08-03 Wietse de Vries , Malvina Nissim

Deploying trained convolutional neural networks (CNNs) to mobile devices is a challenging task because of the simultaneous requirements of the deployed model to be fast, lightweight and accurate. Designing and training a CNN architecture…

Machine Learning · Computer Science 2019-12-02 Ramit Pahwa , Manoj Ghuhan Arivazhagan , Ankur Garg , Siddarth Krishnamoorthy , Rohit Saxena , Sunav Choudhary

Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even…

Computation and Language · Computer Science 2021-12-20 Ofir Zafrir , Guy Boudoukh , Peter Izsak , Moshe Wasserblat

Model compression is an essential technique for deploying deep neural networks (DNNs) on power and memory-constrained resources. However, existing model-compression methods often rely on human expertise and focus on parameters' local…

Computer Vision and Pattern Recognition · Computer Science 2022-07-04 Sixing Yu , Arya Mazaheri , Ali Jannesari

Large language models such as Open AI's Generative Pre-trained Transformer (GPT) models are proficient at answering questions, but their knowledge is confined to the information present in their training data. This limitation renders them…

Computation and Language · Computer Science 2023-08-24 Saba Rahimi , Tucker Balch , Manuela Veloso

Dictionary learning and component analysis are part of one of the most well-studied and active research fields, at the intersection of signal and image processing, computer vision, and statistical machine learning. In dictionary learning,…

Machine Learning · Statistics 2017-07-27 Mehdi Bahri , Yannis Panagakis , Stefanos Zafeiriou

In this paper we propose and study a technique to reduce the number of parameters and computation time in fully-connected layers of neural networks using Kronecker product, at a mild cost of the prediction quality. The technique proceeds by…

Neural and Evolutionary Computing · Computer Science 2015-07-23 Shuchang Zhou , Jia-Nan Wu

Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dynamical process operating on an energy landscape. We propose…

Machine Learning · Computer Science 2026-05-04 Nima Dehmamy , Benjamin Hoover , Bishwajit Saha , Leo Kozachkov , Jean-Jacques Slotine , Dmitry Krotov

The rapid advancement of large language models, such as the Generative Pre-trained Transformer (GPT) series, has had significant implications across various disciplines. In this study, we investigate the potential of the state-of-the-art…

Computation and Language · Computer Science 2023-09-06 Yunhao Yang , Anshul Tomar

Transformer-based pretrained models like BERT, GPT-2 and T5 have been finetuned for a large number of natural language processing (NLP) tasks, and have been shown to be very effective. However, while finetuning, what changes across layers…

Computation and Language · Computer Science 2023-11-09 Pavan Kalyan Reddy Neerudu , Subba Reddy Oota , Mounika Marreddy , Venkateswara Rao Kagita , Manish Gupta

We prove theoretically that generalization improves not only through data scaling but also by compressing internal representations. To operationalize this insight, we introduce the Information Bottleneck Language Modeling (IBLM) objective,…

Machine Learning · Computer Science 2025-10-23 Fangyuan Yu