English
Related papers

Related papers: LaTIM: Measuring Latent Token-to-Token Interaction…

200 papers

In image fusion tasks, images from different sources possess distinct characteristics. This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics.Mamba, as a…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Zihan Cao , Xiao Wu , Liang-Jian Deng , Yu Zhong

State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs during training and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Weiming Ren , Wentao Ma , Huan Yang , Cong Wei , Ge Zhang , Wenhu Chen

A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Fanhu Zeng , Hao Tang , Yihua Shao , Siyu Chen , Ling Shao , Yan Wang

Mamba, a selective state-space model (SSM), has emerged as an efficient alternative to Transformers for speech modeling, enabling long-sequence processing with linear complexity. While effective in speech separation, existing approaches,…

Sound · Computer Science 2026-01-26 Ke Xue , Chang Sun , Rongfei Fan , Jing Wang , Han Hu

Recently, deep learning models have achieved excellent performance in hyperspectral image (HSI) classification. Among the many deep models, Transformer has gradually attracted interest for its excellence in modeling the long-range…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Lingbo Huang , Yushi Chen , Xin He

Denoising is a crucial preprocessing step for hyperspectral images (HSIs) due to noise arising from intra-imaging mechanisms and environmental factors. Long-range spatial-spectral correlation modeling is beneficial for HSI denoising but…

Image and Video Processing · Electrical Eng. & Systems 2024-08-06 Guanyiman Fu , Fengchao Xiong , Jianfeng Lu , Jun Zhou

In this paper, we analyze the computational limitations of Mamba and State-space Models (SSMs) by using the circuit complexity framework. Despite Mamba's stateful design and recent attention as a strong candidate to outperform Transformers,…

Computational Complexity · Computer Science 2025-02-21 Yifang Chen , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song

The recent empirical success of Mamba and other selective state space models (SSMs) has renewed interest in non-attention architectures for sequence modeling, yet their theoretical foundations remain underexplored. We present a first-step…

Machine Learning · Computer Science 2026-02-16 Mugunthan Shandirasegaran , Hongkang Li , Songyang Zhang , Meng Wang , Shuai Zhang

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

State Space Models (SSMs) like Mamba2 are a promising alternative to Transformers, with faster theoretical training and inference times -- especially for long context lengths. Recent work on Matryoshka Representation Learning -- and its…

Machine Learning · Computer Science 2024-10-10 Abhinav Shukla , Sai Vemprala , Aditya Kusupati , Ashish Kapoor

Selective state space models (SSMs), such as Mamba, achieve strong per-token expressivity by making the time discretization step $\Tilde{\Delta}$ a learned function of the input. However, in doing so, $\Tilde{\Delta}$ ceases to represent a…

Machine Learning · Computer Science 2026-05-12 Taylan Soydan , Miguel A. Bessa , Dirk Mohr , Rui Barreira

A key claim in recent work on Selective State Space Models is that selectivity, the ability to focus on relevant information while filtering irrelevant inputs, requires breaking the Linear Time-Invariant (LTI) property through time-varying…

Systems and Control · Electrical Eng. & Systems 2026-03-13 Umberto Casti , Giacomo Baggio , Sandro Zampieri , Fabio Pasqualetti

By sharing complementary perceptual information, multi-agent collaborative perception fosters a deeper understanding of the environment. Recent studies on collaborative perception mostly utilize CNNs or Transformers to learn feature…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Yang Li , Quan Yuan , Guiyang Luo , Xiaoyuan Fu , Xuanhan Zhu , Yujia Yang , Rui Pan , Jinglin Li

State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated due to their ability to model global context, their…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Hyun-kyu Ko , Youbin Kim , Jihyeon Park , Dongheok Park , Gyeongjin Kang , Wonjun Cho , Hyung Yi , Eunbyung Park

Image restoration requires simultaneously preserving fine-grained local structures and maintaining long-range spatial coherence. While convolutional networks struggle with limited receptive fields, and Transformers incur quadratic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Mohammed Hassanin , Nour Moustafa , Weijian Deng , Ibrahim Radwan

Efficiently modeling sequences with infinite context length has long been a challenging problem. Previous approaches have either suffered from quadratic computational complexity or limited extrapolation ability in length generalization. In…

Computation and Language · Computer Science 2025-03-03 Liliang Ren , Yang Liu , Yadong Lu , Yelong Shen , Chen Liang , Weizhu Chen

We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive…

Computation and Language · Computer Science 2025-06-10 Deqian Kong , Minglu Zhao , Dehong Xu , Bo Pang , Shu Wang , Edouardo Honig , Zhangzhang Si , Chuan Li , Jianwen Xie , Sirui Xie , Ying Nian Wu

Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Jindong Jiang , Xiuyu Li , Zhijian Liu , Muyang Li , Guo Chen , Zhiqi Li , De-An Huang , Guilin Liu , Zhiding Yu , Kurt Keutzer , Sungjin Ahn , Jan Kautz , Hongxu Yin , Yao Lu , Song Han , Wonmin Byeon

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Siavash Shams , Sukru Samet Dindar , Xilin Jiang , Nima Mesgarani

Sequence modeling plays a vital role across various domains, with recurrent neural networks being historically the predominant method of performing these tasks. However, the emergence of transformers has altered this paradigm due to their…