English
Related papers

Related papers: Balancing Cost and Benefit with Tied-Multi Transfo…

200 papers

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

Networking and Internet Architecture · Computer Science 2025-11-04 Junhe Zhang , Wanli Ni , Pengwei Wang , Dongyu Wang

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Computation and Language · Computer Science 2024-04-19 Pengfei Wu , Jiahao Liu , Zhuocheng Gong , Qifan Wang , Jinpeng Li , Jingang Wang , Xunliang Cai , Dongyan Zhao

This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers. Layer fusion can significantly reduce…

Machine Learning · Computer Science 2020-07-30 James O' Neill , Greg Ver Steeg , Aram Galstyan

Federated learning has been extensively studied and applied due to its ability to ensure data security in distributed environments while building better models. However, clients participating in federated learning still face limitations, as…

Machine Learning · Computer Science 2026-01-06 Jingxuan Zhou , Weidong Bao , Ji Wang , Dayu Zhang , Xiongtao Zhang , Yaohong Zhang

This paper introduces DeCAL, a new method for tokenwise compression. DeCAL uses an encoder-decoder language model pretrained with denoising to learn to produce high-quality, general-purpose compressed representations from the encoder. DeCAL…

Computation and Language · Computer Science 2025-10-23 Sameer Panwar

Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some…

Computer Vision and Pattern Recognition · Computer Science 2020-06-12 Pavel Kaloshin

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Yangyang Xu , Yibo Yang , Lefei Zhang

Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Weichao Lan , Liang Lan

Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision models (LVM). Model compression methods reduce the memory…

Machine Learning · Computer Science 2024-04-09 Yehui Tang , Yunhe Wang , Jianyuan Guo , Zhijun Tu , Kai Han , Hailin Hu , Dacheng Tao

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP)…

Computation and Language · Computer Science 2019-11-07 Xindian Ma , Peng Zhang , Shuai Zhang , Nan Duan , Yuexian Hou , Dawei Song , Ming Zhou

Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To…

Artificial Intelligence · Computer Science 2023-06-06 Viktoriia Chekalina , Georgii Novikov , Julia Gusak , Ivan Oseledets , Alexander Panchenko

In end-to-end speech translation, speech and text pre-trained models improve translation quality. Recently proposed models simply connect the pre-trained models of speech and text as encoder and decoder. Therefore, only the information from…

Computation and Language · Computer Science 2023-05-29 Yuta Nishikawa , Satoshi Nakamura

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

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

Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…

Applications · Statistics 2024-03-25 Haisheng Fu , Feng Liang , Jie Liang , Zhenman Fang , Guohe Zhang , Jingning Han

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant…

Computation and Language · Computer Science 2021-02-12 Zuchao Li , Zhuosheng Zhang , Hai Zhao , Rui Wang , Kehai Chen , Masao Utiyama , Eiichiro Sumita

Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, we consider several ways to make multilingual NMT faster at…

Computation and Language · Computer Science 2021-11-09 Alexandre Berard , Dain Lee , Stéphane Clinchant , Kweonwoo Jung , Vassilina Nikoulina

We explore the application of very deep Transformer models for Neural Machine Translation (NMT). Using a simple yet effective initialization technique that stabilizes training, we show that it is feasible to build standard Transformer-based…

Computation and Language · Computer Science 2020-10-16 Xiaodong Liu , Kevin Duh , Liyuan Liu , Jianfeng Gao

A recent body of work has demonstrated that Transformer embeddings can be linearly decomposed into well-defined sums of factors, that can in turn be related to specific network inputs or components. There is however still a dearth of work…

Computation and Language · Computer Science 2023-10-12 Timothee Mickus , Raúl Vázquez

Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on…

Computation and Language · Computer Science 2017-05-08 Jacob Devlin
‹ Prev 1 3 4 5 6 7 10 Next ›