English
Related papers

Related papers: 2Mamba2Furious: Linear in Complexity, Competitive …

200 papers

Transformers have proven effective in language modeling but are limited by high computational and memory demands that grow quadratically with input sequence length. State space models (SSMs) offer a promising alternative by reducing…

Hardware Architecture · Computer Science 2025-08-06 Dongho Yoon , Gungyu Lee , Jaewon Chang , Yunjae Lee , Dongjae Lee , Minsoo Rhu

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

Machine Learning · Computer Science 2026-05-26 Chunyuan Deng , Yizhe Zhang , Rui-Jie Zhu , Yuanyuan Xu , Jiarui Liu , T. S. Eugene Ng , Hanjie Chen

The Softmax attention mechanism in Transformer models is notoriously computationally expensive, particularly due to its quadratic complexity, posing significant challenges in vision applications. In contrast, linear attention provides a far…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Qihang Fan , Huaibo Huang , Ran He

Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However,…

Machine Learning · Computer Science 2025-03-07 Michael Zhang , Simran Arora , Rahul Chalamala , Alan Wu , Benjamin Spector , Aaryan Singhal , Krithik Ramesh , Christopher Ré

Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…

Information Retrieval · Computer Science 2025-05-08 Qianru Zhang , Liang Qu , Honggang Wen , Dong Huang , Siu-Ming Yiu , Nguyen Quoc Viet Hung , Hongzhi Yin

Mamba extends earlier state space models (SSMs) by introducing input-dependent dynamics, and has demonstrated strong empirical performance across a range of domains, including language modeling, computer vision, and foundation models.…

Machine Learning · Computer Science 2025-05-15 Annan Yu , N. Benjamin Erichson

Transformers and their variants have achieved great success in speech processing. However, their multi-head self-attention mechanism is computationally expensive. Therefore, one novel selective state space model, Mamba, has been proposed as…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-04 Yang Xiao , Rohan Kumar Das

Multi-modality image fusion aims to integrate the merits of images from different sources and render high-quality fusion images. However, existing feature extraction and fusion methods are either constrained by inherent local reduction bias…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Chenguang Zhu , Shan Gao , Huafeng Chen , Guangqian Guo , Chaowei Wang , Yaoxing Wang , Chen Shu Lei , Quanjiang Fan

Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the…

Computation and Language · Computer Science 2022-02-18 Zhen Qin , Weixuan Sun , Hui Deng , Dongxu Li , Yunshen Wei , Baohong Lv , Junjie Yan , Lingpeng Kong , Yiran Zhong

Recent advancements in medical imaging have resulted in more complex and diverse images, with challenges such as high anatomical variability, blurred tissue boundaries, low organ contrast, and noise. Traditional segmentation methods…

Image and Video Processing · Electrical Eng. & Systems 2024-11-01 Yufeng Jiang , Zongxi Li , Xiangyan Chen , Haoran Xie , Jing Cai

The quadratic computational complexity of self-attention in diffusion transformers (DiT) introduces substantial computational costs in high-resolution image generation. While the linear-complexity Mamba model emerges as a potential…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Yuan Yao , Yicong Hong , Difan Liu , Long Mai , Feng Liu , Jiebo Luo

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Kewei Zhang , Ye Huang , Yufan Deng , Jincheng Yu , Junsong Chen , Huan Ling , Enze Xie , Daquan Zhou

Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal…

Machine Learning · Computer Science 2024-11-19 Yuhong Chou , Man Yao , Kexin Wang , Yuqi Pan , Ruijie Zhu , Yiran Zhong , Yu Qiao , Jibin Wu , Bo Xu , Guoqi Li

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

Vision Transformers have achieved impressive performance in video classification, while suffering from the quadratic complexity caused by the Softmax attention mechanism. Some studies alleviate the computational costs by reducing the number…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Kaiyue Lu , Zexiang Liu , Jianyuan Wang , Weixuan Sun , Zhen Qin , Dong Li , Xuyang Shen , Hui Deng , Xiaodong Han , Yuchao Dai , Yiran Zhong

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

Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due the quadratic complexity of multi-head self-attention…

Machine Learning · Computer Science 2024-09-05 Ryan Whetten , Titouan Parcollet , Adel Moumen , Marco Dinarelli , Yannick Estève

Attention mechanisms have been widely used to capture long-range dependencies among nodes in Graph Transformers. Bottlenecked by the quadratic computational cost, attention mechanisms fail to scale in large graphs. Recent improvements in…

Machine Learning · Computer Science 2024-02-02 Chloe Wang , Oleksii Tsepa , Jun Ma , Bo Wang

"This work has been submitted to the lEEE for possible publication. Copyright may be transferred without noticeafter which this version may no longer be accessible." Time series modeling serves as the cornerstone of real-world applications,…

Machine Learning · Computer Science 2025-04-04 Sijie Xiong , Shuqing Liu , Cheng Tang , Fumiya Okubo , Haoling Xiong , Atsushi Shimada

Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in…