English
Related papers

Related papers: Linear Attention for Efficient Bidirectional Seque…

200 papers

Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising approach for improving the inference efficiency of LLMs without requiring…

Computation and Language · Computer Science 2025-12-24 Yanhong Li , Songlin Yang , Shawn Tan , Mayank Mishra , Rameswar Panda , Jiawei Zhou , Yoon Kim

Transformers are increasingly adopted for modeling and forecasting time-series, yet their internal mechanisms remain poorly understood from a dynamical systems perspective. In contrast to classical autoregressive and state-space models,…

Machine Learning · Computer Science 2025-12-25 Gregory Duthé , Nikolaos Evangelou , Wei Liu , Ioannis G. Kevrekidis , Eleni Chatzi

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the High-Frequency Trading (HFT), forecasting for trading purposes is even a more challenging task…

Computational Engineering, Finance, and Science · Computer Science 2019-06-11 Dat Thanh Tran , Alexandros Iosifidis , Juho Kanniainen , Moncef Gabbouj

Linear attention mitigates the quadratic complexity of softmax attention but suffers from a critical loss of expressiveness. We identify two primary causes: (1) The normalization operation cancels the query norm, which breaks the…

Machine Learning · Computer Science 2026-05-26 Weikang Meng , Yadan Luo , Liangyu Huo , Yingjian Li , Yaowei Wang , Xin Li , Zheng Zhang

Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing, which provide only correlational insights and coarse causal control. This work proposes replacing nonlinearities in…

Machine Learning · Computer Science 2024-12-03 Narmeen Oozeer , Sinem Erisken , Alice Rigg

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Lei Zhu , Xinjiang Wang , Zhanghan Ke , Wayne Zhang , Rynson Lau

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…

Computation and Language · Computer Science 2018-11-02 Maha Elbayad , Laurent Besacier , Jakob Verbeek

Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to…

Computer Vision and Pattern Recognition · Computer Science 2017-09-19 Lin Wu , Yang Wang

Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision. Like neural network layers, these attention mechanisms are often…

Machine Learning · Computer Science 2024-06-21 Tan M. Nguyen , Tam Nguyen , Nhat Ho , Andrea L. Bertozzi , Richard G. Baraniuk , Stanley J. Osher

Efficiently training LLMs with long sequences is important yet challenged by the massive computation and memory requirements. Sequence parallelism has been proposed to tackle these problems, but existing methods suffer from scalability or…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-27 Diandian Gu , Peng Sun , Qinghao Hu , Ting Huang , Xun Chen , Yingtong Xiong , Guoteng Wang , Qiaoling Chen , Shangchun Zhao , Jiarui Fang , Yonggang Wen , Tianwei Zhang , Xin Jin , Xuanzhe Liu

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Vision Transformers (ViTs) have recently taken computer vision by storm. However, the softmax attention underlying ViTs comes with a quadratic complexity in time and memory, hindering the application of ViTs to high-resolution images. We…

Computer Vision and Pattern Recognition · Computer Science 2025-02-17 Chuanyang Zheng

The Linear Attention Recurrent Neural Network (LARNN) is a recurrent attention module derived from the Long Short-Term Memory (LSTM) cell and ideas from the consciousness Recurrent Neural Network (RNN). Yes, it LARNNs. The LARNN uses…

Machine Learning · Computer Science 2018-08-17 Guillaume Chevalier

Lane detection is a crucial perception task for all levels of automated vehicles (AVs) and Advanced Driver Assistance Systems, particularly in mixed-traffic environments where AVs must interact with human-driven vehicles (HDVs) and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Sandeep Patil , Yongqi Dong , Haneen Farah , Hans Hellendoorn

Most of neural approaches to relation classification have focused on finding short patterns that represent the semantic relation using Convolutional Neural Networks (CNNs) and those approaches have generally achieved better performances…

Computation and Language · Computer Science 2017-11-02 Jonggu Kim , Jong-Hyeok Lee

Sequence generative models with RNN variants, such as LSTM, GRU, show promising performance on abstractive document summarization. However, they still have some issues that limit their performance, especially while deal-ing with long…

Computation and Language · Computer Science 2018-09-19 Kamal Al-Sabahi , Zhang Zuping , Yang Kang

Modeling three-dimensional (3D) turbulence by neural networks is difficult because 3D turbulence is highly-nonlinear with high degrees of freedom and the corresponding simulation is memory-intensive. Recently, the attention mechanism has…

Fluid Dynamics · Physics 2022-11-28 Wenhui Peng , Zelong Yuan , Zhijie Li , Jianchun Wang

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Machine Learning · Computer Science 2022-11-30 Bosheng Qin , Juncheng Li , Siliang Tang , Yueting Zhuang

Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL). Despite their success in showing such emergent abilities, the scale and complexity of larger models also lead to…

Computation and Language · Computer Science 2025-06-03 Chengwei Qin , Wenhan Xia , Fangkai Jiao , Chen Chen , Yuchen Hu , Bosheng Ding , Ruirui Chen , Shafiq Joty

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan