English
Related papers

Related papers: Fast Transformer Decoding: One Write-Head is All Y…

200 papers

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Computation and Language · Computer Science 2025-09-19 Yanming Kang , Giang Tran , Hans De Sterck

For supervised speech enhancement, contextual information is important for accurate spectral mapping. However, commonly used deep neural networks (DNNs) are limited in capturing temporal contexts. To leverage long-term contexts for tracking…

Audio and Speech Processing · Electrical Eng. & Systems 2022-10-13 Xinmeng Xu , Jianjun Hao

We revisit a basic question in sequence modeling: is explicit self-attention actually necessary for strong performance and reasoning? We argue that standard multi-head attention is best seen as a form of tensor lifting: hidden vectors are…

Machine Learning · Computer Science 2025-12-23 Zhang Chong

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Kewei Zhang , Ye Huang , Yufan Deng , Jincheng Yu , Junsong Chen , Huan Ling , Enze Xie , Daquan Zhou

The transformer architecture is widely used in machine learning models and consists of two alternating sublayers: attention heads and MLPs. We prove that an MLP neuron can be implemented by a masked attention head with internal dimension 1…

Machine Learning · Computer Science 2023-09-18 Robert Huben , Valerie Morris

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Sergey Zagoruyko , Nikos Komodakis

We study length generalization in sequence models on a composite problem involving both state tracking and associative recall. Prior work finds that recurrent networks handle state tracking well but struggle with recall, whereas…

Machine Learning · Computer Science 2025-10-02 Buu Phan , Reza Ebrahimi , Sanjay Haresh , Roland Memisevic

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically show that large…

Machine Learning · Computer Science 2025-10-29 Tiberiu Musat

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

Computation and Language · Computer Science 2016-09-28 Lei Yu , Jan Buys , Phil Blunsom

Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value…

Machine Learning · Computer Science 2025-12-30 Xiaowei Wang

Deep attention models have advanced the modelling of sequential data across many domains. For language modelling in particular, the Transformer-XL -- a Transformer augmented with a long-range memory of past activations -- has been shown to…

Machine Learning · Computer Science 2020-07-08 Jack W. Rae , Ali Razavi

The multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models. Given a sequence length $k$, attention matrices…

Machine Learning · Computer Science 2024-02-07 Sitan Chen , Yuanzhi Li

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

More and more evidence has shown that strengthening layer interactions can enhance the representation power of a deep neural network, while self-attention excels at learning interdependencies by retrieving query-activated information.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Yanwen Fang , Yuxi Cai , Jintai Chen , Jingyu Zhao , Guangjian Tian , Guodong Li

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

At present, people usually use some methods based on convolutional neural networks (CNNs) for Electroencephalograph (EEG) decoding. However, CNNs have limitations in perceiving global dependencies, which is not adequate for common EEG…

Signal Processing · Electrical Eng. & Systems 2021-06-23 Yonghao Song , Xueyu Jia , Lie Yang , Longhan Xie

The attention mechanism forms the foundational blocks for transformer language models. Recent approaches show that scaling the model achieves human-level performance. However, with increasing demands for scaling and constraints on hardware…

Computation and Language · Computer Science 2024-07-16 Sai Sena Chinnakonduru , Astarag Mohapatra

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state…

Machine Learning · Computer Science 2026-05-22 Hangyue Zhao , Paul Caillon , Erwan Fagnou , Alexandre Allauzen

Transformer neural networks (TNNs) are being applied across a widening range of application domains, including natural language processing (NLP), machine translation, and computer vision (CV). Their popularity is largely attributed to the…

Hardware Architecture · Computer Science 2025-12-22 Ehsan Kabir , Md. Arafat Kabir , Austin R. J. Downey , Jason D. Bakos , David Andrews , Miaoqing Huang

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li