English
Related papers

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

200 papers

Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we systematically investigate Mamba's representational properties…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Timing Yang , Guoyizhe Wei , Alan Yuille , Feng Wang

Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision tasks. In this paper, we reveal that the powerful Mamba…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Dongchen Han , Ziyi Wang , Zhuofan Xia , Yizeng Han , Yifan Pu , Chunjiang Ge , Jun Song , Shiji Song , Bo Zheng , Gao Huang

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

State space models (SSMs) have emerged as an efficient alternative to transformer-based models, offering linear complexity that scales better than transformers. One of the latest advances in SSMs, Mamba, introduces a selective scan…

Machine Learning · Computer Science 2025-03-03 Junpeng Wang , Chin-Chia Michael Yeh , Uday Singh Saini , Mahashweta Das

Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a computational burden. In NLP, Mamba has surfaced as an…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Hui Lu , Albert Ali Salah , Ronald Poppe

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

The Transformer architecture is widely deployed in many popular and impactful Large Language Models. At its core is the attention mechanism for calculating correlations between pairs of tokens. Performing an attention computation takes…

Machine Learning · Computer Science 2025-05-26 Josh Alman , Hantao Yu

Transformers and Mamba, initially invented for natural language processing, have inspired backbone architectures for visual recognition. Recent studies integrated Local Attention Transformers with Mamba to capture both local details and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Meng Lou , Yunxiang Fu , Yizhou Yu

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

Machine Learning · Computer Science 2025-06-30 Junxiong Wang , Daniele Paliotta , Avner May , Alexander M. Rush , Tri Dao

The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space…

Machine Learning · Computer Science 2026-03-03 Han Guo , Songlin Yang , Tarushii Goel , Eric P. Xing , Tri Dao , Yoon Kim

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Computation and Language · Computer Science 2024-10-22 Wangjie You , Zecheng Tang , Juntao Li , Lili Yao , Min Zhang

In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…

Artificial Intelligence · Computer Science 2026-03-20 Yan Li , Yifei Xing , Xiangyuan Lan , Xin Li , Haifeng Chen , Dongmei Jiang

Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when dealing with high-resolution inputs. In contrast, linear…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Dongchen Han , Yifan Pu , Zhuofan Xia , Yizeng Han , Xuran Pan , Xiu Li , Jiwen Lu , Shiji Song , Gao Huang

As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits its applicability to vision tasks. In contrast, Linear Attention shares a similar formulation…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Qihang Fan , Huaibo Huang , Yuang Ai , Ran He

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Eric C. Larson

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-29 Xiangyu Zhang , Qiquan Zhang , Hexin Liu , Tianyi Xiao , Xinyuan Qian , Beena Ahmed , Eliathamby Ambikairajah , Haizhou Li , Julien Epps

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

Recent Transformer-based diffusion models have shown remarkable performance, largely attributed to the ability of the self-attention mechanism to accurately capture both global and local contexts by computing all-pair interactions among…

Computer Vision and Pattern Recognition · Computer Science 2024-09-20 Yunxiang Fu , Chaoqi Chen , Yizhou Yu

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
‹ Prev 1 2 3 10 Next ›