English
Related papers

Related papers: On the Generalization Properties of Selective Stat…

200 papers

Current automatic speech recognition systems struggle with modeling long speech sequences due to high quadratic complexity of Transformer-based models. Selective state space models such as Mamba has performed well on long-sequence modeling…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-30 Xiaoxue Gao , Nancy F. Chen

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

Machine Learning · Computer Science 2025-01-29 J. Pablo Muñoz , Jinjie Yuan , Nilesh Jain

Selective state-space models (SSMs) are an emerging alternative to the Transformer, offering the unique advantage of parallel training and sequential inference. Although these models have shown promising performance on a variety of tasks,…

Machine Learning · Computer Science 2025-07-08 Aleksandar Terzić , Michael Hersche , Giacomo Camposampiero , Thomas Hofmann , Abu Sebastian , Abbas Rahimi

In recent years, Transformers have become the de-facto architecture for long-term sequence forecasting (LTSF), but faces challenges such as quadratic complexity and permutation invariant bias. A recent model, Mamba, based on selective state…

Machine Learning · Computer Science 2024-05-28 Xiuding Cai , Yaoyao Zhu , Xueyao Wang , Yu Yao

State Space Models (SSMs) have emerged as promising alternatives to attention mechanisms, with the Mamba architecture demonstrating impressive performance and linear complexity for processing long sequences. However, the fundamental…

Machine Learning · Computer Science 2026-01-22 Tianyi Chen , Pengxiao Lin , Zhiwei Wang , Zhi-Qin John Xu

In the realm of time series forecasting (TSF), it is imperative for models to adeptly discern and distill hidden patterns within historical time series data to forecast future states. Transformer-based models exhibit formidable efficacy in…

Machine Learning · Computer Science 2024-04-30 Zihan Wang , Fanheng Kong , Shi Feng , Ming Wang , Xiaocui Yang , Han Zhao , Daling Wang , Yifei Zhang

Speculative decoding has emerged as a promising approach to accelerating large language model (LLM) generation using a fast drafter while maintaining alignment with the target model's distribution. However, existing approaches face a…

Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated…

Sound · Computer Science 2024-06-11 Sarthak Yadav , Zheng-Hua Tan

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

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances, such as Mamba, further enhance SSMs with input-dependent…

Machine Learning · Computer Science 2025-06-24 Zheng Zhan , Liliang Ren , Shuohang Wang , Liyuan Liu , Yang Liu , Yeyun Gong , Yanzhi Wang , Yelong Shen

Recently, recurrent models based on linear state space models (SSMs) have shown promising performance in language modeling (LM), competititve with transformers. However, there is little understanding of the in-principle abilities of such…

Computation and Language · Computer Science 2025-12-15 Yash Sarrof , Yana Veitsman , Michael Hahn

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…

Recently, state space models (SSM), particularly Mamba, have attracted significant attention from scholars due to their ability to effectively balance computational efficiency and performance. However, most existing visual Mamba methods…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Leiye Liu , Miao Zhang , Jihao Yin , Tingwei Liu , Wei Ji , Yongri Piao , Huchuan Lu

State Space Models (SSMs) have emerged as a promising alternative to Transformers for long-context sequence modeling, offering linear $O(N)$ computational complexity compared to the Transformer's quadratic $O(N^2)$ scaling. This paper…

Machine Learning · Computer Science 2026-01-06 Abidemi Koledoye , Chinemerem Unachukwu , Gold Nwobu , Hasin Rana

State-space models (SSMs) have emerged as a potential alternative architecture for building large language models (LLMs) compared to the previously ubiquitous transformer architecture. One theoretical weakness of transformers is that they…

Machine Learning · Computer Science 2025-03-07 William Merrill , Jackson Petty , Ashish Sabharwal

State-Space Models (SSMs) have emerged as an efficient alternative to transformers, yet existing visual SSMs retain deeply ingrained biases from their origins in natural language processing. In this paper, we address these limitations by…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Enis Baty , Alejandro Hernández Díaz , Rebecca Davidson , Chris Bridges , Simon Hadfield

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

Structured state space models (SSMs) have recently emerged as a promising foundation for sequence modeling, with Mamba-based architectures demonstrating strong performance through input-dependent state transitions, albeit at considerable…

Machine Learning · Computer Science 2026-05-28 Hassan Saadatmand , Geoffrey I. Webb , Hamid Rezatofighi , Mahsa Salehi

Transformers have become dominant in large-scale deep learning tasks across various domains, including text, 2D and 3D vision. However, the quadratic complexity of their attention mechanism limits their efficiency as the sequence length…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Nursena Köprücü , Destiny Okpekpe , Antonio Orvieto

Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Haoyang He , Yuhu Bai , Jiangning Zhang , Qingdong He , Hongxu Chen , Zhenye Gan , Chengjie Wang , Xiangtai Li , Guanzhong Tian , Lei Xie