English
Related papers

Related papers: Sequential-Parallel Duality in Prefix Scannable Mo…

200 papers

State space models (SSMs) have emerged as an efficient alternative to transformer-based models, offering linear complexity that scales better than transformers. One of the latest advances in SSMs, Mamba, introduces a selective scan…

Machine Learning · Computer Science 2025-03-03 Junpeng Wang , Chin-Chia Michael Yeh , Uday Singh Saini , Mahashweta Das

Softmax attention is the principle backbone of foundation models for various artificial intelligence applications, yet its quadratic complexity in sequence length can limit its inference throughput in long-context settings. To address this…

Machine Learning · Computer Science 2024-12-10 Jerome Sieber , Carmen Amo Alonso , Alexandre Didier , Melanie N. Zeilinger , Antonio Orvieto

Structured State Space Models (SSMs), which are at the heart of the recently popular Mamba architecture, are powerful tools for sequence modeling. However, their theoretical foundation relies on a complex, multi-stage process of…

Machine Learning · Computer Science 2025-12-23 Sutashu Tomonaga , Kenji Doya , Noboru Murata

Recurrent Neural Networks (RNNs) laid the foundation for sequence modeling, but their intrinsic sequential nature restricts parallel computation, creating a fundamental barrier to scaling. This has led to the dominance of parallelizable…

Machine Learning · Computer Science 2025-11-04 Federico Danieli , Pau Rodriguez , Miguel Sarabia , Xavier Suau , Luca Zappella

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

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

Convolutional neural networks (CNNs) and transformers are widely employed in constructing UNet architectures for medical image segmentation tasks. However, CNNs struggle to model long-range dependencies, while transformers suffer from…

Image and Video Processing · Electrical Eng. & Systems 2025-03-26 Shaolei Zhang , Jinyan Liu , Tianyi Qian , Xuesong Li

State-space modeling has emerged as a powerful paradigm for sequence analysis in various tasks such as natural language processing, time-series forecasting, and signal processing. In this work, we propose an \emph{Adaptive State-Space…

Machine Learning · Computer Science 2025-07-31 Alice Zhang , Chao Li

In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transformer-based architectures to forecast the subsequent item…

Artificial Intelligence · Computer Science 2024-12-25 Ziwei Liu , Qidong Liu , Yejing Wang , Wanyu Wang , Pengyue Jia , Maolin Wang , Zitao Liu , Yi Chang , Xiangyu Zhao

Due to the long-range modeling ability and linear complexity property, Mamba has attracted considerable attention in point cloud analysis. Despite some interesting progress, related work still suffers from imperfect point cloud…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Kanglin Qu , Pan Gao , Qun Dai , Zhanzhi Ye , Rui Ye , Yuanhao Sun

Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high…

Machine Learning · Computer Science 2019-07-02 Diego Maupomé , Marie-Jean Meurs

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing a vertically chunked…

Computation and Language · Computer Science 2026-04-21 Tobias Grantner , Emanuel Sallinger , Martin Flechl

Foundational models have significantly advanced in natural language processing (NLP) and computer vision (CV), with the Transformer architecture becoming a standard backbone. However, the Transformer's quadratic complexity poses challenges…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Lv Tang , HaoKe Xiao , Peng-Tao Jiang , Hao Zhang , Jinwei Chen , Bo Li

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

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

Modern recurrent architectures, such as xLSTM and Mamba, have recently challenged the Transformer in language modeling. However, their structure constrains their applicability to sequences only or requires processing multi-dimensional data…

Machine Learning · Computer Science 2025-06-16 Korbinian Pöppel , Richard Freinschlag , Thomas Schmied , Wei Lin , Sepp Hochreiter

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as…

Machine Learning · Computer Science 2026-05-08 Yulong Huang , Xiang Liu , Hongxiang Huang , Xiaopeng Lin , Zunchang Liu , Xiaowen Chu , Zeke Xie , Bojun Cheng

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. While early architectures were developed primarily as a scalable alternative to Gaussian…