English
Related papers

Related papers: Delta Attention: Fast and Accurate Sparse Attentio…

200 papers

How much information do NLP tasks really need from a transformer's attention mechanism at application-time (inference)? From recent work, we know that there is sparsity in transformers and that the floating-points within its computation can…

Computation and Language · Computer Science 2021-06-03 Tianchu Ji , Shraddhan Jain , Michael Ferdman , Peter Milder , H. Andrew Schwartz , Niranjan Balasubramanian

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Tongcheng Fang , Hanling Zhang , Ruiqi Xie , Zhuo Han , Xin Tao , Tianchen Zhao , Pengfei Wan , Wenbo Ding , Wanli Ouyang , Xuefei Ning , Yu Wang

The quadratic complexity of standard attention mechanisms poses a significant scalability bottleneck for large language models (LLMs) in long-context scenarios. While hybrid attention strategies that combine sparse and full attention within…

Computation and Language · Computer Science 2026-01-29 Zecheng Tang , Quantong Qiu , Yi Yang , Zhiyi Hong , Haiya Xiang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are…

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

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Computation and Language · Computer Science 2021-09-13 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Machine Learning · Computer Science 2024-10-17 Yingyu Liang , Heshan Liu , Zhenmei Shi , Zhao Song , Zhuoyan Xu , Junze Yin

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…

Computation and Language · Computer Science 2021-10-07 Biao Zhang , Ivan Titov , Rico Sennrich

Transformers have achieved remarkable performance in multivariate time series(MTS) forecasting due to their capability to capture long-term dependencies. However, the canonical attention mechanism has two key limitations: (1) its quadratic…

Machine Learning · Computer Science 2024-07-17 Yifan Zhang , Rui Wu , Sergiu M. Dascalu , Frederick C. Harris

Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Haopeng Li , Shitong Shao , Wenliang Zhong , Zikai Zhou , Lichen Bai , Hui Xiong , Zeke Xie

One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses the entire sequence length, however, the actual attention being used is sparse. Humans…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Marc Estafanous

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Computation and Language · Computer Science 2022-04-08 Zuzana Jelčicová , Marian Verhelst

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Machine Learning · Computer Science 2025-11-20 Jintao Zhang , Chendong Xiang , Haofeng Huang , Jia Wei , Haocheng Xi , Jun Zhu , Jianfei Chen

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

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

Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is $\alpha$-entmax attention, a differentiable sparse alternative to…

Machine Learning · Computer Science 2026-04-17 Nuno Gonçalves , Hugo Pitorro , Vlad Niculae , Edoardo Ponti , Lei Li , Andre Martins , Marcos Treviso

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

In this work we introduce a new transformer architecture called SparseDistilBERT (SDBERT), which is a combination of sparse attention and knowledge distillantion (KD). We implemented sparse attention mechanism to reduce quadratic dependency…

Computation and Language · Computer Science 2022-08-23 Devaraju Vinoda , Pawan Kumar Yadav

The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of $O(N^2)$, compared to $O(N)$ for linear transformations. When handling large sequence lengths,…

Machine Learning · Computer Science 2025-10-02 Jintao Zhang , Jia Wei , Haofeng Huang , Pengle Zhang , Jun Zhu , Jianfei Chen