English
Related papers

Related papers: Approaching I/O-optimality for Approximate Attenti…

200 papers

FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full quantization difficult. We identify three main obstacles to integer-only…

Machine Learning · Computer Science 2026-04-29 Sehyeon Oh , Yongin Kwon , Jemin Lee

A central problem related to transformers can be stated as follows: given two $n \times d$ matrices $Q$ and $K$, and a non-negative function $f$, define the matrix $A$ as follows: (1) apply the function $f$ to each entry of the $n \times n$…

Machine Learning · Computer Science 2024-10-10 Ravindran Kannan , Chiranjib Bhattacharyya , Praneeth Kacham , David P. Woodruff

The attention mechanism in text generation is memory-bounded due to its sequential characteristics. Therefore, off-chip memory accesses should be minimized for faster execution. Although previous methods addressed this by pruning…

Hardware Architecture · Computer Science 2024-07-23 Junyoung Park , Myeonggu Kang , Yunki Han , Yanggon Kim , Jaekang Shin , Lee-Sup Kim

As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity. While many efficient…

Machine Learning · Computer Science 2025-07-11 Zhengyu Tian , Anantha Padmanaban Krishna Kumar , Hemant Krishnakumar , Reza Rawassizadeh

Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear…

Machine Learning · Computer Science 2025-07-08 Naoki Nishikawa , Rei Higuchi , Taiji Suzuki

We introduce Monte-Carlo Attention (MCA), a randomized approximation method for reducing the computational cost of self-attention mechanisms in Transformer architectures. MCA exploits the fact that the importance of each token in an input…

Machine Learning · Computer Science 2022-02-01 Hyunjun Kim , JeongGil Ko

Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the…

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the…

Computation and Language · Computer Science 2017-06-20 Edouard Grave , Armand Joulin , Moustapha Cissé , David Grangier , Hervé Jégou

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottleneck that limits their scalability. Alman and Song (NeurIPS…

Machine Learning · Computer Science 2026-03-20 Maryam Aliakbarpour , Vladimir Braverman , Junze Yin , Haochen Zhang

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

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Over the past 7 years, attention has become one of the most important primitives in deep learning. The primary approach to optimize attention is FlashAttention, which fuses the operation together, drastically improving both the runtime and…

Machine Learning · Computer Science 2024-12-10 Juechu Dong , Boyuan Feng , Driss Guessous , Yanbo Liang , Horace He

When designing an algorithm, one cares about arithmetic/computational complexity, but data movement (I/O) complexity plays an increasingly important role that highly impacts performance and energy consumption. For a given algorithm and a…

Computational Complexity · Computer Science 2024-04-26 Lionel Eyraud-Dubois , Guillaume Iooss , Julien Langou , Fabrice Rastello

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

Computation and Language · Computer Science 2017-07-04 Denny Britz , Melody Y. Guan , Minh-Thang Luong

Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high dimensions. This approach reduces the…

Machine Learning · Computer Science 2024-02-13 Armin Gerami , Monte Hoover , Pranav S. Dulepet , Ramani Duraiswami

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Mohsen Ghafoorian , Denis Korzhenkov , Amirhossein Habibian