English
Related papers

Related papers: Fundamental Limitations on Subquadratic Alternativ…

200 papers

Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Dingkang Liang , Xin Zhou , Wei Xu , Xingkui Zhu , Zhikang Zou , Xiaoqing Ye , Xiao Tan , Xiang Bai

Despite several successes in document understanding, the practical task for long document understanding is largely under-explored due to several challenges in computation and how to efficiently absorb long multimodal input. Most current…

Computation and Language · Computer Science 2022-08-18 Hai Pham , Guoxin Wang , Yijuan Lu , Dinei Florencio , Cha Zhang

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…

Machine Learning · Computer Science 2021-10-22 Liu Liu , Zheng Qu , Zhaodong Chen , Yufei Ding , Yuan Xie

Mamba is an efficient sequence model that rivals Transformers and demonstrates significant potential as a foundational architecture for various tasks. Quantization is commonly used in neural networks to reduce model size and computational…

Machine Learning · Computer Science 2025-03-12 Zukang Xu , Yuxuan Yue , Xing Hu , Zhihang Yuan , Zixu Jiang , Zhixuan Chen , Jiangyong Yu , Chen Xu , Sifan Zhou , Dawei Yang

In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Shufan Li , Harkanwar Singh , Aditya Grover

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under a hand-crafted patterns and 2) full attention followed by a…

Machine Learning · Computer Science 2022-10-28 Sungjun Cho , Seonwoo Min , Jinwoo Kim , Moontae Lee , Honglak Lee , Seunghoon Hong

Recent advancements in recurrent architectures, such as Mamba and RWKV, have showcased strong language capabilities. Unlike transformer-based models, these architectures encode all contextual information into a fixed-size state, leading to…

Computation and Language · Computer Science 2026-01-14 Yingfa Chen , Xinrong Zhang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms, such as linear and hybrid attention, have been developed. A…

Machine Learning · Computer Science 2026-02-03 Xiaowei Ye , Xiaoyu He , Chao Liao , Chen Wu , Pinyan Lu

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

Computation and Language · Computer Science 2022-05-05 Guy D. Rosin , Kira Radinsky

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

Machine Learning · Computer Science 2024-05-08 Dongseong Hwang , Weiran Wang , Zhuoyuan Huo , Khe Chai Sim , Pedro Moreno Mengibar

In multivariate time-series forecasting (MTSF), extracting the temporal correlations of the input sequences is crucial. While popular Transformer-based predictive models can perform well, their quadratic computational complexity results in…

Machine Learning · Computer Science 2024-07-23 Shusen Ma , Yu Kang , Peng Bai , Yun-Bo Zhao

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…

Computation and Language · Computer Science 2026-02-02 Aryaman Arora , Neil Rathi , Nikil Roashan Selvam , Róbert Csordás , Dan Jurafsky , Christopher Potts

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability…

Machine Learning · Computer Science 2026-05-19 Rui An , Haohao Qu , Wenqi Fan , Xuequn Shang , Qing Li

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Computation and Language · Computer Science 2026-05-20 Jiaoda Li , Ryan Cotterell

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading…

Machine Learning · Computer Science 2025-12-16 Peng Lu , Jerry Huang , Qiuhao Zeng , Xinyu Wang , Boxing Chen , Philippe Langlais , Yufei Cui