English
Related papers

Related papers: Cascade Token Selection for Transformer Attention …

200 papers

A method is presented for accelerating inference in transformer language models by exploiting the low effective rank of the token activation manifold at each layer. The method decomposes each activation vector into a subspace component and…

Machine Learning · Computer Science 2026-05-06 Stephen J. Thomas

Transformers are widely used for their ability to capture data relations in sequence processing, with great success for a wide range of static tasks. However, the computational and memory footprint of their main component, i.e., the Scaled…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Ginés Carreto Picón , Illia Oleksiienko , Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Transformers achieve state-of-the-art results across many tasks, but their uniform application of quadratic self-attention to every token at every layer makes them computationally expensive. We introduce DTRNet (Dynamic Token Routing…

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

Computation and Language · Computer Science 2026-05-26 Spandan Pratyush

Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for each prediction, Cross Attention scans the full set of $\mathcal{O}(N)$ tokens. In practice, however,…

Machine Learning · Computer Science 2024-03-04 Leo Feng , Frederick Tung , Hossein Hajimirsadeghi , Yoshua Bengio , Mohamed Osama Ahmed

Transformers have demonstrated remarkable success across vision, language, and video. Yet, increasing task complexity has led to larger models and more tokens, raising the quadratic cost of self-attention and the overhead of GPU memory…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Joonmyung Choi , Sanghyeok Lee , Byungoh Ko , Eunseo Kim , Jihyung Kil , Hyunwoo J. Kim

The attention mechanism is becoming increasingly popular in Natural Language Processing (NLP) applications, showing superior performance than convolutional and recurrent architectures. However, attention becomes the compution bottleneck…

Hardware Architecture · Computer Science 2024-07-22 Hanrui Wang , Zhekai Zhang , Song Han

Deep neural networks have shown excellent prospects in speech separation tasks. However, obtaining good results while keeping a low model complexity remains challenging in real-world applications. In this paper, we provide a bio-inspired…

Sound · Computer Science 2023-03-31 Kai Li , Runxuan Yang , Xiaolin Hu

Over recent years, the Transformer has become a fundamental building block for sequence modeling architectures. Yet at its core is the use of self-attention, whose memory and computational cost grow quadratically with the sequence length…

Machine Learning · Computer Science 2025-04-02 Qiuhao Zeng , Jerry Huang , Peng Lu , Gezheng Xu , Boxing Chen , Charles Ling , Boyu Wang

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Leheng Zhang , Wei Long , Yawei Li , Xingyu Zhou , Xiaorui Zhao , Shuhang Gu

Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that…

Machine Learning · Computer Science 2017-10-11 Jiaqi Guan , Yang Liu , Qiang Liu , Jian Peng

Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Dong-Jae Lee , Jiwan Hur , Jaehyun Choi , Jaemyung Yu , Junmo Kim

We present Neural Attention Search (NAtS), a framework that automatically evaluates the importance of each token within a sequence and determines if the corresponding token can be dropped after several steps. This approach can efficiently…

Computation and Language · Computer Science 2025-10-24 Difan Deng , Marius Lindauer

The attention interaction matrix $QK^{\top}$ contains two entangled computations: a skew-symmetric component that redistributes information between positions (routing) and a symmetric component that scales mutual relevance (filtering). We…

Machine Learning · Computer Science 2026-05-20 Shafayeth Jamil , Rehan Kapadia

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

Transformer-based end-to-end (E2E) automatic speech recognition (ASR) systems have recently gained wide popularity, and are shown to outperform E2E models based on recurrent structures on a number of ASR tasks. However, like other E2E…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-30 Mohan Li , Catalin Zorila , Rama Doddipatla

Despite the success of vision transformers (ViTs), they still suffer from significant drops in accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we observe that the attention mechanism of ViTs tends to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Yong Guo , David Stutz , Bernt Schiele

Transformers have advanced the field of natural language processing (NLP) on a variety of important tasks. At the cornerstone of the Transformer architecture is the multi-head attention (MHA) mechanism which models pairwise interactions…

Computation and Language · Computer Science 2021-06-01 Lin Zheng , Zhiyong Wu , Lingpeng Kong