English
Related papers

Related papers: Sharing Attention Weights for Fast Transformer

200 papers

In this paper, we introduce the prior knowledge, multi-scale structure, into self-attention modules. We propose a Multi-Scale Transformer which uses multi-scale multi-head self-attention to capture features from different scales. Based on…

Computation and Language · Computer Science 2019-12-03 Qipeng Guo , Xipeng Qiu , Pengfei Liu , Xiangyang Xue , Zheng Zhang

Scaled dot-product attention applies a softmax function on the scaled dot-product of queries and keys to calculate weights and then multiplies the weights and values. In this work, we study how to improve the learning of scaled dot-product…

Computer Vision and Pattern Recognition · Computer Science 2023-03-17 Kaikai Zhao , Norimichi Ukita

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Computation and Language · Computer Science 2023-11-27 Nathan Brown , Ashton Williamson , Tahj Anderson , Logan Lawrence

Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of…

Machine Learning · Computer Science 2021-05-18 Swetha Mandava , Szymon Migacz , Alex Fit Florea

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Antoine Miech , Jean-Baptiste Alayrac , Ivan Laptev , Josef Sivic , Andrew Zisserman

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks,…

Computation and Language · Computer Science 2018-08-01 Hasan Sait Arslan , Mark Fishel , Gholamreza Anbarjafari

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Dimitrios Kafetzis , Ramin Khalili , Iordanis Koutsopoulos

Non-Autoregressive machine Translation (NAT) models have demonstrated significant inference speedup but suffer from inferior translation accuracy. The common practice to tackle the problem is transferring the Autoregressive machine…

Computation and Language · Computer Science 2021-05-18 Yongchang Hao , Shilin He , Wenxiang Jiao , Zhaopeng Tu , Michael Lyu , Xing Wang

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Since the introduction of the Transformer architecture for large language models, the softmax-based attention layer has faced increasing scrutinity due to its quadratic-time computational complexity. Attempts have been made to replace it…

Machine Learning · Computer Science 2026-02-02 Robert Forchheimer

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation…

Computation and Language · Computer Science 2025-06-02 Shantanu Acharya , Fei Jia , Boris Ginsburg

Point Transformers are near state-of-the-art models for classification, segmentation, and detection tasks on Point Cloud data. They utilize a self attention based mechanism to model large range spatial dependencies between multiple point…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Kartik Gupta , Rahul Vippala , Sahima Srivastava

Efficient Transformers have been developed for long sequence modeling, due to their subquadratic memory and time complexity. Sparse Transformer is a popular approach to improving the efficiency of Transformers by restricting self-attention…

Machine Learning · Computer Science 2023-02-01 Aosong Feng , Irene Li , Yuang Jiang , Rex Ying

In this paper, we seek solutions for reducing the computation complexity of transformer-based models for speech representation learning. We evaluate 10 attention algorithms; then, we pre-train the transformer-based model with those…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-04 Tsung-Han Wu , Chun-Chen Hsieh , Yen-Hao Chen , Po-Han Chi , Hung-yi Lee

In recent years, a great deal of attention has been paid to the Transformer network for speech recognition tasks due to its excellent model performance. However, the Transformer network always involves heavy computation and large number of…

Sound · Computer Science 2023-04-12 Guangyong Wei , Zhikui Duan , Shiren Li , Guangguang Yang , Xinmei Yu , Junhua Li

We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix" input tokens. These linear mixers, along with standard…

Computation and Language · Computer Science 2022-05-30 James Lee-Thorp , Joshua Ainslie , Ilya Eckstein , Santiago Ontanon

Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the…

Computation and Language · Computer Science 2021-01-01 Jiatao Gu , Xiang Kong

Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…

Computation and Language · Computer Science 2025-11-04 Juan Gabriel Kostelec , Qinghai Guo

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Chen Zhu , Wei Ping , Chaowei Xiao , Mohammad Shoeybi , Tom Goldstein , Anima Anandkumar , Bryan Catanzaro
‹ Prev 1 3 4 5 6 7 10 Next ›