English
Related papers

Related papers: SpAtten: Efficient Sparse Attention Architecture w…

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

The quadratic complexity of attention mechanisms limits the efficiency of Large Language Models (LLMs) on long-text tasks. Recently, methods that dynamically estimate block importance have enabled efficient block sparse attention, leading…

Computation and Language · Computer Science 2026-04-01 Yixuan Wang , Huang He , Siqi Bao , Hua Wu , Haifeng Wang , Qingfu Zhu , Wanxiang Che

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference…

Computation and Language · Computer Science 2026-02-03 Zimeng Wu , Donghao Wang , Chaozhe Jin , Jiaxin Chen , Yunhong Wang

The Transformer architecture has shown to be a powerful tool for a wide range of tasks. It is based on the self-attention mechanism, which is an inherently computationally expensive operation with quadratic computational complexity: memory…

Machine Learning · Computer Science 2024-02-07 Adjorn van Engelenhoven , Nicola Strisciuglio , Estefanía Talavera

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xuewen Liu , Zhikai Li , Jing Zhang , Mengjuan Chen , Qingyi Gu

Sparse attention, which selectively attends to a subset of tokens in the context was supposed to be efficient. However, its theoretical reduction in FLOPs has rarely translated into wall-clock speed-up over its dense attention counterparts…

Computation and Language · Computer Science 2025-02-06 Xihui Lin , Yunan Zhang , Suyu Ge , Liliang Ren , Barun Patra , Vishrav Chaudhary , Hao Peng , Xia Song

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…

Image and Video Processing · Electrical Eng. & Systems 2024-04-12 Jiing-Ping Wang , Ming-Guang Lin , An-Yeu , Wu

Long-context modeling is crucial for next-generation language models, yet the high computational cost of standard attention mechanisms poses significant computational challenges. Sparse attention offers a promising direction for improving…

Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token sparsity, i.e. only a few pivotal tokens significantly contribute…

Machine Learning · Computer Science 2025-06-05 Aditya Desai , Shuo Yang , Alejandro Cuadron , Matei Zaharia , Joseph E. Gonzalez , Ion Stoica

As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…

Computation and Language · Computer Science 2024-12-10 James Vo

In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications. Visual token pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Qihui Zhu , Tao Zhang , Yuchen Wang , Zijian Wen , Mengjie Zhang , Shuangwu Chen , Xiaobin Tan , Jian Yang , Yang Liu , Zhenhua Dong , Xianzhi Yu , Yinfei Pan

In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…

Machine Learning · Computer Science 2024-07-19 Ghadeer Jaradat , Mohammed Tolba , Ghada Alsuhli , Hani Saleh , Mahmoud Al-Qutayri , Thanos Stouraitis , Baker Mohammad

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Xiaohuan Pei , Tao Huang , Chang Xu

On-device running Large Language Models (LLMs) is nowadays a critical enabler towards preserving user privacy. We observe that the attention operator falls back from the special-purpose NPU to the general-purpose CPU/GPU because of…

Performance · Computer Science 2026-04-09 Wangsong Yin , Daliang Xu , Mengwei Xu , Gang Huang , Xuanzhe Liu

This paper introduces Syntactic Attention Pruning (SAP), a novel method for effectively pruning attention heads in Transformer models. Unlike conventional approaches that rely solely on mathematical analysis of model weights and…

Computation and Language · Computer Science 2025-12-23 Tzu-Yun Lee , Ding-Yong Hong , Jan-Jan Wu

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Computation and Language · Computer Science 2025-07-24 Luoyang Sun , Cheng Deng , Jiwen Jiang , Xinjian Wu , Haifeng Zhang , Lei Chen , Lionel Ni , Jun Wang

In modern large language models (LLMs), increasing the context length is crucial for improving comprehension and coherence in long-context, multi-modal, and retrieval-augmented language generation. While many recent transformer models…

Computation and Language · Computer Science 2025-01-24 Heejun Lee , Geon Park , Youngwan Lee , Jaduk Suh , Jina Kim , Wonyoung Jeong , Bumsik Kim , Hyemin Lee , Myeongjae Jeon , Sung Ju Hwang

Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using…

Hardware Architecture · Computer Science 2024-11-12 Zihang Song , Prabodh Katti , Osvaldo Simeone , Bipin Rajendran

We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks. While attention is a staple of modern network architectures, it is also notoriously expensive to deploy due to resource…

Machine Learning · Computer Science 2026-02-11 Tobias Schröder , Lester Mackey

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Qiankun Ma , Ziyao Zhang , Haofei Wang , Jie Chen , Zhen Song , Hairong Zheng