English
Related papers

Related papers: WildCat: Near-Linear Attention in Theory and Pract…

200 papers

As its core computation, a self-attention mechanism gauges pairwise correlations across the entire input sequence. Despite favorable performance, calculating pairwise correlations is prohibitively costly. While recent work has shown the…

Machine Learning · Computer Science 2022-09-02 Amir Yazdanbakhsh , Ashkan Moradifirouzabadi , Zheng Li , Mingu Kang

Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized GPU kernels. For example, FlashAttention-2/3 (exact, GPU-optimized implementations of…

Machine Learning · Computer Science 2026-04-21 Sahil Joshi , Agniva Chowdhury , Amar Kanakamedala , Ekam Singh , Evan Tu , Anshumali Shrivastava

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

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

We present a unified framework for quantum sensitivity sampling, extending the advantages of quantum computing to a broad class of classical approximation problems. Our unified framework provides a streamlined approach for constructing…

Data Structures and Algorithms · Computer Science 2025-09-23 Zhao Song , David P. Woodruff , Lichen Zhang

The attention mechanism has demonstrated superior performance for inference over nodes in graph neural networks (GNNs), however, they result in a high computational burden during both training and inference. We propose FastGAT, a method to…

Machine Learning · Computer Science 2020-10-06 Rakshith S Srinivasa , Cao Xiao , Lucas Glass , Justin Romberg , Jimeng Sun

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to…

Computation and Language · Computer Science 2023-06-13 Xianming Li , Zongxi Li , Xiaotian Luo , Haoran Xie , Xing Lee , Yingbin Zhao , Fu Lee Wang , Qing Li

Sparse attention improves LLM inference efficiency by selecting a subset of key-value entries, but at the cost of potential accuracy degradation. In particular, omitting critical KV entries can induce substantial errors in model outputs.…

Machine Learning · Computer Science 2026-05-12 Mohsen Dehghankar , Abolfazl Asudeh

We revisit the classic #Knapsack problem, which asks to count the Boolean points $(x_1,\dots,x_n)\in\{0,1\}^n$ in a given half-space $\sum_{i=1}^nW_ix_i\le T$. This #P-complete problem admits $(1\pm\epsilon)$-approximation. Before this…

Data Structures and Algorithms · Computer Science 2024-10-30 Weiming Feng , Ce Jin

While the integration of transformers in vision models have yielded significant improvements on vision tasks they still require significant amounts of computation for both training and inference. Restricted attention mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Steven Walton , Ali Hassani , Xingqian Xu , Zhangyang Wang , Humphrey Shi

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Machine Learning · Computer Science 2026-02-13 Kaicheng Xiao , Haotian Li , Liran Dong , Guoliang Xing

We present SparseAttnNet, a new hierarchical attention-driven framework for efficient image classification that adaptively selects and processes only the most informative pixels from images. Traditional convolutional neural networks…

Image and Video Processing · Electrical Eng. & Systems 2025-05-13 Elad Yoshai , Dana Yagoda-Aharoni , Eden Dotan , Natan T. Shaked

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Machine Learning · Computer Science 2024-03-19 Praneeth Kacham , Vahab Mirrokni , Peilin Zhong

Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing…

Machine Learning · Computer Science 2025-03-04 Haoran You , Zhanyi Sun , Huihong Shi , Zhongzhi Yu , Yang Zhao , Yongan Zhang , Chaojian Li , Baopu Li , Yingyan Celine Lin

Recent advances in sparse voxel representations have significantly improved the quality of 3D content generation, enabling high-resolution modeling with fine-grained geometry. However, existing frameworks suffer from severe computational…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Yiwen Chen , Zhihao Li , Yikai Wang , Hu Zhang , Qin Li , Chi Zhang , Guosheng Lin

Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the…

Machine Learning · Computer Science 2016-05-26 Miltiadis Allamanis , Hao Peng , Charles Sutton

Although deep convolutional neural networks achieve state-of-the-art performance across nearly all image classification tasks, their decisions are difficult to interpret. One approach that offers some level of interpretability by design is…

Computer Vision and Pattern Recognition · Computer Science 2019-12-10 Gamaleldin F. Elsayed , Simon Kornblith , Quoc V. Le

Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their…

Computation and Language · Computer Science 2021-07-09 Pedro Henrique Martins , Vlad Niculae , Zita Marinho , André Martins

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and…

Machine Learning · Computer Science 2025-06-05 Marcial Sanchis-Agudo , Yuning Wang , Roger Arnau , Luca Guastoni , Jasmin Lim , Karthik Duraisamy , Ricardo Vinuesa