English
Related papers

Related papers: HySparse: A Hybrid Sparse Attention Architecture w…

200 papers

The transformer architecture has driven breakthroughs in recent years on tasks which require modeling pairwise relationships between sequential elements, as is the case in natural language understanding. However, long seqeuences pose a…

Computation and Language · Computer Science 2024-03-26 Heejun Lee , Jina Kim , Jeffrey Willette , Sung Ju Hwang

Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…

Computation and Language · Computer Science 2026-04-16 Jusen Du , Jiaxi Hu , Tao Zhang , Weigao Sun , Yu Cheng

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due to its quadratic complexity. Consequently, sparse attention…

Computation and Language · Computer Science 2026-01-07 Junxiang Qiu , Shuo Wang , Zhengsu Chen , Hengheng Zhang , Jinda Lu , Changcheng Li , Qi Tian

Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced…

Hardware Architecture · Computer Science 2024-11-26 Haibin Wu , Wenming Li , Kai Yan , Zhihua Fan , Peiyang Wu , Yuqun Liu , Yanhuan Liu , Ziqing Qiang , Meng Wu , Kunming Liu , Xiaochun Ye , Dongrui Fan

Self-attention in transformer models is an incremental associative memory that maps key vectors to value vectors. One way to speed up self-attention is to employ GPU-compatible vector search algorithms based on standard partitioning methods…

Computation and Language · Computer Science 2025-06-04 Pierre-Emmanuel Mazaré , Gergely Szilvasy , Maria Lomeli , Francisco Massa , Naila Murray , Hervé Jégou , Matthijs Douze

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Yifan Zhou , Zeqi Xiao , Tianyi Wei , Shuai Yang , Xingang Pan

Although Transformers have successfully transitioned from their language modelling origins to image-based applications, their quadratic computational complexity remains a challenge, particularly for dense prediction. In this paper we…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Yutong Xie , Jianpeng Zhang , Yong Xia , Anton van den Hengel , Qi Wu

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Computation and Language · Computer Science 2025-05-13 Zihan Qiu , Zekun Wang , Bo Zheng , Zeyu Huang , Kaiyue Wen , Songlin Yang , Rui Men , Le Yu , Fei Huang , Suozhi Huang , Dayiheng Liu , Jingren Zhou , Junyang Lin

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

Computation and Language · Computer Science 2022-10-12 Xiaofeng Zhang , Yikang Shen , Zeyu Huang , Jie Zhou , Wenge Rong , Zhang Xiong

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…

Computation and Language · Computer Science 2026-04-21 Zhiyuan Shi , Qibo Qiu , Feng Xue , Zhonglin Jiang , Li Yu , Jian Jiang , Xiaofei He , Wenxiao Wang

Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Jiahui Wang , Zuyan Liu , Yongming Rao , Jiwen Lu

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer…

Machine Learning · Computer Science 2024-10-08 Lijie Yang , Zhihao Zhang , Zhuofu Chen , Zikun Li , Zhihao Jia

While Transformer self-attention offers strong parallelism, the Key-Value (KV) cache grows linearly with sequence length and becomes a bottleneck for inference efficiency. Multi-head latent attention was recently developed to compress the…

Machine Learning · Computer Science 2025-11-04 Keqi Deng , Philip C. Woodland

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Qirui Li , Guangcong Zheng , Qi Zhao , Jie Li , Bin Dong , Yiwu Yao , Xi Li

The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose \textbf{STA-Attention}, a framework that utilizes Top-K…

Machine Learning · Computer Science 2025-12-12 Qingsen Ma , Dianyun Wang , Jiaming Lyu , Yaoye Wang , Lechen Ning , Sujie Zhu , Zhenbo Xu , Liuyu Xiang , Huining Li , Huijia Wu , Zhaofeng He

Long-context inference increasingly operates over CPU-resident KV caches, either because decoding-time KV states exceed GPU memory capacity or because disaggregated prefill-decode systems place KV data in host memory. Although block-sparse…

Machine Learning · Computer Science 2026-05-11 Feiyu Yao , Zhixiong Niu , Xiaqing Li , Yongqiang Xiong , Juan Fang , Qian Wang

Video diffusion Transformer (DiT) models excel in generative quality but hit major computational bottlenecks when producing high-resolution, long-duration videos. The quadratic complexity of full attention leads to prohibitively high…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Chenlu Zhan , Wen Li , Chuyu Shen , Jun Zhang , Suhui Wu , Hao Zhang

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality but suffers from large Key-Value (KV) cache memory…

Artificial Intelligence · Computer Science 2025-12-25 Esmail Gumaan

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

Machine Learning · Computer Science 2024-12-24 Ziyang Wu , Tianjiao Ding , Yifu Lu , Druv Pai , Jingyuan Zhang , Weida Wang , Yaodong Yu , Yi Ma , Benjamin D. Haeffele