English
Related papers

Related papers: ELSA: Exact Linear-Scan Attention for Fast and Mem…

200 papers

This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation…

Machine Learning · Computer Science 2026-05-21 Weinuo Ou

Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning. The performance of local self-attention (LSA) is just on par with convolution and inferior to dynamic filters, which…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Jingkai Zhou , Pichao Wang , Fan Wang , Qiong Liu , Hao Li , Rong Jin

Transformer models rely heavily on the scaled dot-product attention (SDPA) operation, typically implemented as FlashAttention. Characterized by its frequent interleaving of matrix multiplications and softmax operations, FlashAttention fails…

Hardware Architecture · Computer Science 2025-12-09 Jiawei Lin , Yuanlong Li , Guokai Chen , Thomas Bourgeat

Spiking neural networks (SNNs) exploit event-driven and addition-only computation to substantially improve efficiency for intelligent computation. A key temporal property of SNNs, elastic inference, allows outputs to emerge progressively,…

Hardware Architecture · Computer Science 2026-05-21 Kang You , Chen Nie , Lee Jun Yan , Ziling Wei , Cheng Zou , Zekai Xu , Yu Feng , Honglan Jiang , Zhezhi He

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 cost of softmax attention limits Transformer scalability in high-resolution vision. We introduce Infinite Self-Attention (InfSA), a spectral reformulation that treats each attention layer as a diffusion step on a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Giorgio Roffo , Hazem Abdelkawy , Nilli Lavie , Luke Palmer

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Machine Learning · Computer Science 2025-10-03 Yifei Zuo , Yutong Yin , Zhichen Zeng , Ang Li , Banghua Zhu , Zhaoran Wang

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Scaling attention faces a critical bottleneck: the $\mathcal{O}(n^2)$ quadratic computational cost of softmax attention, which limits its application in long-sequence domains. While linear attention mechanisms reduce this cost to…

Machine Learning · Computer Science 2025-12-10 Ashkan Shahbazi , Ping He , Ali Abbasi , Yikun Bai , Xinran Liu , Elaheh Akbari , Darian Salehi , Navid NaderiAlizadeh , Soheil Kolouri

Recent advance in sparse attention mechanisms has demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs). Native Sparse Attention (NSA), one state-of-the-art…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-14 Ran Yan , Youhe Jiang , Zhuoming Chen , Haohui Mai , Beidi Chen , Binhang Yuan

Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a novel framework that enhances MLA inference for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-05 Pengcuo Dege , Qiuming Luo , Rui Mao , Chang Kong

The next significant step in the evolution and proliferation of artificial intelligence technology will be the integration of neural network (NN) models within embedded and mobile systems. This calls for the design of compact, energy…

Machine Learning · Computer Science 2020-02-05 Elham Azari , Sarma Vrudhula

Linear attention reduces the quadratic cost of softmax attention to $\mathcal{O}(T)$, but its memory state grows as $\mathcal{O}(T)$ in Frobenius norm, causing progressive interference between stored associations. We introduce…

Machine Learning · Computer Science 2026-05-13 Vishal Pandey , Gopal Singh

Training large language models (LLMs) at the network edge faces fundamental challenges arising from device resource constraints, severe data heterogeneity, and heightened privacy risks. To address these challenges, we propose ELSA…

Machine Learning · Computer Science 2026-03-10 Xiaohong Yang , Tong Xie , Minghui Liwang , Chikai Shang , Yang Lu , Zhenzhen Jiao , Liqun Fu , Seyyedali Hosseinalipour

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

FlashAttention-style online softmax enables exact attention computation with linear memory by streaming score tiles through on-chip memory and maintaining a running maximum and normalizer. However, as attention kernels approach peak…

Machine Learning · Computer Science 2026-04-15 Yupeng Sun , Yanzhao Li , Zhiqiang Zou , Bai Du , Zhiyuan Zhang , Hui Dong , Gaoyige Fan , Hui Wang

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

Artificial Intelligence · Computer Science 2026-02-13 Hanno Ackermann , Hong Cai , Mohsen Ghafoorian , Amirhossein Habibian

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

Linear RNNs with gating recently demonstrated competitive performance compared to Transformers in language modeling. Although their linear compute scaling in sequence length offers theoretical runtime advantages over Transformers, realizing…

Machine Learning · Computer Science 2025-12-30 Maximilian Beck , Korbinian Pöppel , Phillip Lippe , Sepp Hochreiter

In this paper, we introduce Exact Flow Linear Attention~(EFLA), an exact-flow formulation of delta-rule linear attention. We show that the delta-rule update can be interpreted as an explicit Euler discretization of an underlying…

Machine Learning · Computer Science 2026-05-11 Jingdi Lei , Di Zhang , Soujanya Poria
‹ Prev 1 2 3 10 Next ›