English
Related papers

Related papers: Customizing the Inductive Biases of Softmax Attent…

200 papers

Transformers are widely used across various applications, many of which yield sparse or partially filled attention matrices. Examples include attention masks designed to reduce the quadratic complexity of attention, sequence packing…

Machine Learning · Computer Science 2024-09-25 Agniv Sharma , Jonas Geiping

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or…

Machine Learning · Computer Science 2026-02-16 Jintao Zhang , Haoxu Wang , Kai Jiang , Kaiwen Zheng , Youhe Jiang , Ion Stoica , Jianfei Chen , Jun Zhu , Joseph E. Gonzalez

Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation. For these long context length applications, the length of the input prompt poses a…

Linear attention is an efficient attention mechanism that has recently emerged as a promising alternative to conventional softmax attention. With its ability to process tokens in linear computational complexities, linear attention, in…

Computation and Language · Computer Science 2024-01-17 Zhen Qin , Weigao Sun , Dong Li , Xuyang Shen , Weixuan Sun , Yiran Zhong

Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the attention matrix during the softmax function computation.…

Machine Learning · Computer Science 2025-02-13 Yichuan Deng , Zhao Song , Jing Xiong , Chiwun Yang

Apart from the high accuracy of machine learning models, what interests many researchers in real-life problems (e.g., fraud detection, credit scoring) is to find hidden patterns in data; particularly when dealing with their challenging…

Attention layers apply a sequence-to-sequence mapping whose parameters depend on the pairwise interactions of the input elements. However, without any structural assumptions, memory and compute scale quadratically with the sequence length.…

Machine Learning · Computer Science 2025-09-26 Evgenii Egorov , Hanno Ackermann , Markus Nagel , Hong Cai

The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These…

Computation and Language · Computer Science 2026-02-04 Difan Deng , Andreas Bentzen Winje , Lukas Fehring , Marius Lindauer

State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we investigate the global structure of attention scores computed…

Machine Learning · Computer Science 2021-06-17 Srinadh Bhojanapalli , Ayan Chakrabarti , Himanshu Jain , Sanjiv Kumar , Michal Lukasik , Andreas Veit

Attention mechanism remains the defining operator in Transformers since it provides expressive global credit assignment, yet its $O(N^2 d)$ time and memory cost in sequence length $N$ makes long-context modeling expensive and often forces…

Information Retrieval · Computer Science 2026-03-04 Chenghao Zhang , Chao Feng , Yuanhao Pu , Xunyong Yang , Wenhui Yu , Xiang Li , Yongqi Liu , Lantao Hu , Kaiqiao Zhan , Han Li , Kun Gai

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

Self-attention has become an important and widely used neural network component that helped to establish new state-of-the-art results for various applications, such as machine translation and automatic speech recognition (ASR). However, the…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-08 Niko Moritz , Takaaki Hori , Jonathan Le Roux

Prompt learning has become a prevalent strategy for adapting vision-language foundation models (VLMs) such as CLIP to downstream tasks. With the emergence of large language models (LLMs), recent studies have explored the potential of using…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Yubin Wang , Xinyang Jiang , De Cheng , Wenli Sun , Dongsheng Li , Cairong Zhao

Self-attention has greatly contributed to the success of the widely used Transformer architecture by enabling learning from data with long-range dependencies. In an effort to improve performance, a gated attention model that leverages a…

Machine Learning · Computer Science 2026-02-03 Viet Nguyen , Tuan Minh Pham , Thinh Cao , Tan Dinh , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

Large Language Models (LLMs) are pivotal in advancing natural language processing but often struggle with complex reasoning tasks due to inefficient attention distributions. In this paper, we explore the effect of increased computed tokens…

Computation and Language · Computer Science 2024-06-25 Bingli Liao , Danilo Vasconcellos Vargas

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Computation and Language · Computer Science 2025-05-13 Kai Hua , Steven Wu , Ge Zhang , Ke Shen

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through test-time optimization of a learnable latent variable. We observe that attention, as the core module of MLLMs,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-08 Mingrui Wu , Xinyue Cai , Jiayi Ji , Jiale Li , Oucheng Huang , Gen Luo , Hao Fei , Guannan Jiang , Xiaoshuai Sun , Rongrong Ji

Many advanced Large Language Model (LLM) applications require long-context processing, but the self-attention module becomes a bottleneck during the prefilling stage of inference due to its quadratic time complexity with respect to sequence…

Machine Learning · Computer Science 2025-06-02 Xiaodong Ji , Hailin Zhang , Fangcheng Fu , Bin Cui

The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their capacity for complex reasoning and broaden their applicability across diverse scenarios.…

Computation and Language · Computer Science 2026-05-20 Wenxuan Li , Chengruidong Zhang , Huiqiang Jiang , Yucheng Li , Yuqing Yang , Lili Qiu