English
Related papers

Related papers: Samba: Simple Hybrid State Space Models for Effici…

200 papers

State-space language models such as Mamba match Transformer quality while permitting linear complexity inference, yet still comprise billions of parameters that hinder deployment. Existing one-shot pruning methods are tailored to attention…

Machine Learning · Computer Science 2025-06-12 Kaiwen Tuo , Huan Wang

When predicting the next token in a sequence, vanilla transformers compute attention over all previous tokens, resulting in quadratic scaling of compute with sequence length. State-space models compress the entire sequence of tokens into a…

Machine Learning · Computer Science 2024-11-27 Yash Akhauri , Safeen Huda , Mohamed S. Abdelfattah

Whispered speech recognition presents significant challenges for conventional automatic speech recognition systems, particularly when combined with dialect variation. However, utilizing an efficient method to solve this problem using a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-30 Aref Farhadipour , Homayoon Beigi , Volker Dellwo , Hadi Veisi

Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Hongda Liu , Longguang Wang , Ye Zhang , Ziru Yu , Yulan Guo

Abnormality detection in medical imaging is a critical task requiring both high efficiency and accuracy to support effective diagnosis. While convolutional neural networks (CNNs) and Transformer-based models are widely used, both face…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Yao Wang , Dong Yang , Zhi Qiao , Wenjian Huang , Liuzhi Yang , Zhen Qian

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models…

In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the…

Computation and Language · Computer Science 2025-02-11 Pengfei Hu , Zhenrong Zhang , Jiefeng Ma , Shuhang Liu , Jun Du , Jianshu Zhang

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Vincent Tao Hu , Stefan Andreas Baumann , Ming Gui , Olga Grebenkova , Pingchuan Ma , Johannes Schusterbauer , Björn Ommer

Self attention encoders such as Bidirectional Encoder Representations from Transformers(BERT) scale quadratically with sequence length, making long context modeling expensive. Linear time state space models, such as Mamba, are efficient;…

Computation and Language · Computer Science 2026-03-04 Jinwoong Kim , Sangjin Park

Large language models (LLMs) have made significant advances in complex reasoning tasks, yet they remain bottlenecked by two core challenges: architectural inefficiency due to reliance on Transformers, and a lack of structured fine-tuning…

Machine Learning · Computer Science 2025-05-29 Xueliang Zhao , Wei Wu , Lingpeng Kong

Recent work has shown that attention-based language models excel at recall, the ability to ground generations in tokens previously seen in context. However, the efficiency of attention-based models is bottle-necked during inference by the…

Computation and Language · Computer Science 2025-03-10 Simran Arora , Sabri Eyuboglu , Michael Zhang , Aman Timalsina , Silas Alberti , Dylan Zinsley , James Zou , Atri Rudra , Christopher Ré

State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Parameter-Efficient…

Machine Learning · Computer Science 2026-03-03 Donghyun Lee , Yuhang Li , Ruokai Yin , Shiting Xiao , Priyadarshini Panda

Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amounts of lifelong user…

Information Retrieval · Computer Science 2024-03-26 Jiyuan Yang , Yuanzi Li , Jingyu Zhao , Hanbing Wang , Muyang Ma , Jun Ma , Zhaochun Ren , Mengqi Zhang , Xin Xin , Zhumin Chen , Pengjie Ren

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level…

Machine Learning · Computer Science 2025-04-11 Assaf Ben-Kish , Itamar Zimerman , Shady Abu-Hussein , Nadav Cohen , Amir Globerson , Lior Wolf , Raja Giryes

Efficiently modeling large 2D contexts is essential for various fields including Giga-Pixel Whole Slide Imaging (WSI) and remote sensing. Transformer-based models offer high parallelism but face challenges due to their quadratic complexity…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Jingwei Zhang , Anh Tien Nguyen , Xi Han , Vincent Quoc-Huy Trinh , Hong Qin , Dimitris Samaras , Mahdi S. Hosseini

Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Chuxin Wang , Yixin Zha , Wenfei Yang , Tianzhu Zhang

Human activity recognition (HAR) from inertial sensors is essential for ubiquitous computing, mobile health, and ambient intelligence. Conventional deep models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs),…

Human-Computer Interaction · Computer Science 2025-11-27 Thai-Khanh Nguyen , Uyen Vo , Tan M. Nguyen , Thieu N. Vo , Trung-Hieu Le , Cuong Pham

Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-05-02 Xilin Jiang , Cong Han , Nima Mesgarani

A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. However, RNNs are fundamentally unable to randomly access…

Computation and Language · Computer Science 2025-11-04 Xiang Hu , Jiaqi Leng , Jun Zhao , Kewei Tu , Wei Wu

State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast…

Machine Learning · Computer Science 2026-01-01 Mahdi Karami , Ali Behrouz , Peilin Zhong , Razvan Pascanu , Vahab Mirrokni
‹ Prev 1 3 4 5 6 7 10 Next ›