English
Related papers

Related papers: Simplified State Space Layers for Sequence Modelin…

200 papers

In the quest for next-generation sequence modeling architectures, State Space Models (SSMs) have emerged as a potent alternative to transformers, particularly for their computational efficiency and suitability for dynamical systems. This…

Machine Learning · Computer Science 2024-06-17 Steven Abreu , Jens E. Pedersen , Kade M. Heckel , Alessandro Pierro

The reconstruction and estimation of spatio-temporal patterns poses significant challenges when sensor measurements are limited. The use of mobile sensors adds additional complexity due to the change in sensor locations over time. In such…

Dynamical Systems · Mathematics 2024-07-16 Jiazhong Mei , J. Nathan Kutz

To implement deep learning models on edge devices, model compression methods have been widely recognized as useful. However, it remains unclear which model compression methods are effective for Structured State Space Sequence (S4) models…

Machine Learning · Computer Science 2024-07-02 Haruka Ezoe , Kazuhiro Sato

Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from…

Hardware Architecture · Computer Science 2026-03-24 Saptarshi Mitra , Rachid Karami , Haocheng Xu , Sitao Huang , Hyoukjun Kwon

Spiking neural networks (SNNs) provide an energy-efficient solution by utilizing the spike-based and sparse nature of biological systems. Since the advent of Transformers, SNNs have struggled to compete with artificial networks on long…

Neural and Evolutionary Computing · Computer Science 2024-10-24 Yan Zhong , Ruoyu Zhao , Chao Wang , Qinghai Guo , Jianguo Zhang , Zhichao Lu , Luziwei Leng

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

Sequence modeling is crucial for AI to understand temporal data and detect complex time-dependent patterns. While recurrent neural networks (RNNs), convolutional neural networks (CNNs), and Transformers have advanced in capturing long-range…

Machine Learning · Computer Science 2025-08-08 Shiva Raja , Cansu Demirkiran , Aakash Sarkar , Milos Popovic , Ajay Joshi

We propose a multi-dimensional structured state space (S4) approach to speech enhancement. To better capture the spectral dependencies across the frequency axis, we focus on modifying the multi-dimensional S4 layer with whitening…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-28 Pin-Jui Ku , Chao-Han Huck Yang , Sabato Marco Siniscalchi , Chin-Hui Lee

Spiking neural networks (SNNs) present a promising computing paradigm for neuromorphic processing of event-based sensor data. The resonate-and-fire (RF) neuron, in particular, appeals through its biological plausibility, complex dynamics,…

Neural and Evolutionary Computing · Computer Science 2025-04-02 Thomas E. Huber , Jules Lecomte , Borislav Polovnikov , Axel von Arnim

Existing models encounter bottlenecks in balancing performance and computational efficiency when modeling long sequences. Although the state space model (SSM) has achieved remarkable success in handling long sequence tasks, it still faces…

Machine Learning · Computer Science 2025-05-06 Tongyi Liang , Han-Xiong Li

Convolutional models have been widely used in multiple domains. However, most existing models only use local convolution, making the model unable to handle long-range dependency efficiently. Attention overcomes this problem by aggregating…

Machine Learning · Computer Science 2022-10-18 Yuhong Li , Tianle Cai , Yi Zhang , Deming Chen , Debadeepta Dey

The goal of this paper is to provide a system identification-friendly introduction to the Structured State-space Models (SSMs). These models have become recently popular in the machine learning community since, owing to their…

Systems and Control · Electrical Eng. & Systems 2024-05-21 Fabio Bonassi , Carl Andersson , Per Mattsson , Thomas B. Schön

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

Video diffusion models have recently shown promise for world modeling through autoregressive frame prediction conditioned on actions. However, they struggle to maintain long-term memory due to the high computational cost associated with…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Ryan Po , Yotam Nitzan , Richard Zhang , Berlin Chen , Tri Dao , Eli Shechtman , Gordon Wetzstein , Xun Huang

This work explores the in-context learning capabilities of State Space Models (SSMs) and presents, to the best of our knowledge, the first theoretical explanation of a possible underlying mechanism. We introduce a novel weight construction…

Machine Learning · Computer Science 2025-08-05 Federico Arangath Joseph , Kilian Konstantin Haefeli , Noah Liniger , Caglar Gulcehre

Long-range dependencies are critical for understanding genomic structure and function, yet most conventional methods struggle with them. Widely adopted transformer-based models, while excelling at short-context tasks, are limited by the…

State space models (SSMs) have high performance on long sequence modeling but require sophisticated initialization techniques and specialized implementations for high quality and runtime performance. We study whether a simple alternative…

Machine Learning · Computer Science 2023-02-15 Daniel Y. Fu , Elliot L. Epstein , Eric Nguyen , Armin W. Thomas , Michael Zhang , Tri Dao , Atri Rudra , Christopher Ré

Deep state-space models (Deep SSMs) are becoming popular as effective approaches to model sequence data. They have also been shown to be capable of in-context learning, much like transformers. However, a complete picture of how SSMs might…

Machine Learning · Computer Science 2025-02-19 Neeraj Mohan Sushma , Yudou Tian , Harshvardhan Mestha , Nicolo Colombo , David Kappel , Anand Subramoney

Spiking neural networks (SNNs) are posited as a computationally efficient and biologically plausible alternative to conventional neural architectures, with their core computational framework primarily using the leaky integrate-and-fire…

Neural and Evolutionary Computing · Computer Science 2025-03-18 Malyaban Bal , Abhronil Sengupta

Deep State-Space Models (SSM) demonstrate state-of-the art performance on long-range sequence modeling tasks. While the recurrent structure of SSMs can be efficiently implemented as a convolution or as a parallel scan during training,…