English
Related papers

Related papers: Simple Hardware-Efficient Long Convolutions for Se…

200 papers

A central challenge in sequence modeling is efficiently handling tasks with extended contexts. While recent state-space models (SSMs) have made significant progress in this area, they often lack input-dependent filtering or require…

Machine Learning · Computer Science 2024-10-07 Taylan Soydan , Nikola Zubić , Nico Messikommer , Siddhartha Mishra , Davide Scaramuzza

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,…

Learning multiscale Transformer models has been evidenced as a viable approach to augmenting machine translation systems. Prior research has primarily focused on treating subwords as basic units in developing such systems. However, the…

Computation and Language · Computer Science 2023-05-29 Bei Li , Yi Jing , Xu Tan , Zhen Xing , Tong Xiao , Jingbo Zhu

State space models (SSMs) have recently emerged as a powerful framework for long sequence processing, outperforming traditional methods on diverse benchmarks. Fundamentally, SSMs can generalize both recurrent and convolutional networks and…

Signal Processing · Electrical Eng. & Systems 2025-12-24 Xiaoyu Zhang , Mingtao Hu , Sen Lu , Soohyeon Kim , Eric Yeu-Jer Lee , Yuyang Liu , Wei D. Lu

Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train. Deep state-space models (SSMs) have recently been shown to perform remarkably well on long sequence modeling tasks, and have…

Machine Learning · Computer Science 2023-03-14 Antonio Orvieto , Samuel L Smith , Albert Gu , Anushan Fernando , Caglar Gulcehre , Razvan Pascanu , Soham De

Recent advances in sequence modeling have introduced selective SSMs as promising alternatives to Transformer architectures, offering theoretical computational efficiency and sequence processing advantages. A comprehensive understanding of…

Machine Learning · Computer Science 2025-12-01 Abdullah Al Asif , Mobina Kashaniyan , Sixing Yu , Juan Pablo Muñoz , Ali Jannesari

The quadratic time and memory complexity inherent to self-attention mechanisms, with respect to sequence length, presents a critical computational bottleneck in the training and deployment of large-scale Transformer-based language models.…

Machine Learning · Computer Science 2024-03-19 Praneeth Kacham , Vahab Mirrokni , Peilin Zhong

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

We propose a modular framework for hybrid image restoration that integrates transformer and state-space model (SSM) blocks with a focus on improving runtime efficiency on edge hardware. While transformers provide strong global modeling…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Srinivas Soumitri Miriyala , Sowmya Vajrala , Sravanth Kodavanti , Vikram Nelvoy Rajendiran , Sharan Kumar Allur

Recent advances in attention-free sequence models rely on convolutions as alternatives to the attention operator at the core of Transformers. In particular, long convolution sequence models have achieved state-of-the-art performance in many…

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

The success of self-attention (SA) in Transformer demonstrates the importance of non-local information to image super-resolution (SR), but the huge computing power required makes it difficult to implement lightweight models. To solve this…

Image and Video Processing · Electrical Eng. & Systems 2025-08-18 Yinggan Tang , Quanwei Hu

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Machine Learning · Computer Science 2024-05-07 Yuzhen Mao , Martin Ester , Ke Li

State Space Models (SSMs), developed to tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference. At their core are recurrent dynamical systems that maintain a hidden state, with update costs…

Machine Learning · Computer Science 2026-02-26 Makram Chahine , Philipp Nazari , Daniela Rus , T. Konstantin Rusch

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational network…

Computation and Language · Computer Science 2024-03-06 Wei He , Kai Han , Yehui Tang , Chengcheng Wang , Yujie Yang , Tianyu Guo , Yunhe Wang

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Computation and Language · Computer Science 2022-10-07 Mario Michael Krell , Matej Kosec , Sergio P. Perez , Andrew Fitzgibbon

Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There are existing…

Computation and Language · Computer Science 2022-12-19 Simiao Zuo , Xiaodong Liu , Jian Jiao , Denis Charles , Eren Manavoglu , Tuo Zhao , Jianfeng Gao

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 become the leading alternative to Transformers for sequence modeling. Their primary advantage is efficiency in long-context and long-form generation, enabled by fixed-size memory and linear scaling of…

Machine Learning · Computer Science 2025-10-17 Eran Malach , Omid Saremi , Sinead Williamson , Arwen Bradley , Aryo Lotfi , Emmanuel Abbe , Josh Susskind , Etai Littwin

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…