English
Related papers

Related papers: Efficient Attention via Control Variates

200 papers

Efficient long-sequence generation is a critical challenge for Large Language Models. While recent sparse decoding methods improve efficiency, they suffer from KV cache misalignment, where approximation errors accumulate and degrade…

Computation and Language · Computer Science 2025-06-06 Yutao Sun , Tianzhu Ye , Li Dong , Yuqing Xia , Jian Chen , Yizhao Gao , Shijie Cao , Jianyong Wang , Furu Wei

Mamba has recently garnered attention as an effective backbone for vision tasks. However, its underlying mechanism in visual domains remains poorly understood. In this work, we systematically investigate Mamba's representational properties…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Timing Yang , Guoyizhe Wei , Alan Yuille , Feng Wang

The pursuit of reducing the memory footprint of the self-attention mechanism in multi-headed self attention (MHA) spawned a rich portfolio of methods, e.g., group-query attention (GQA) and multi-head latent attention (MLA). The methods…

Machine Learning · Computer Science 2026-04-01 Timon Klein , Jonas Kusch , Sebastian Sager , Stefan Schnake , Steffen Schotthöfer

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised…

Machine Learning · Statistics 2020-06-11 Jay Heo , Hae Beom Lee , Saehoon Kim , Juho Lee , Kwang Joon Kim , Eunho Yang , Sung Ju Hwang

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Kewei Zhang , Ye Huang , Yufan Deng , Jincheng Yu , Junsong Chen , Huan Ling , Enze Xie , Daquan Zhou

We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on compact domains. Our…

Machine Learning · Computer Science 2025-12-17 Jerry Yao-Chieh Hu , Hude Liu , Hong-Yu Chen , Weimin Wu , Han Liu

We explore the ways that a reference point may direct attention. Utilizing a stochastic choice framework, we provide behavioral foundations for the Reference-Dependent Random Attention Model (RD-RAM). Our characterization result shows that…

Theoretical Economics · Economics 2023-03-21 Matthew Kovach , Elchin Suleymanov

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

We study efficient reasoning under tight compute. We ask how to make structured, correct decisions without increasing test time cost. We add two training only components to small and medium Transformers that also transfer to broader…

Machine Learning · Computer Science 2026-03-11 Rian Atri

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

Machine Learning · Computer Science 2025-10-03 Adam Filipek

Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance. We identify the root cause of this degradation as the…

Machine Learning · Computer Science 2026-02-05 Weikang Meng , Liangyu Huo , Yadan Luo , Yaowei Wang , Yingjian Li , Zheng Zhang

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this…

Computer Vision and Pattern Recognition · Computer Science 2023-02-01 Jiaming Han , Yuqiang Ren , Jian Ding , Ke Yan , Gui-Song Xia

The adoption of pre-trained visual representations (PVRs), leveraging features from large-scale vision models, has become a popular paradigm for training visuomotor policies. However, these powerful representations can encode a broad range…

Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the level of complexity in attention infrastructure, and the…

We propose the Multi-Head Density Adaptive Attention Mechanism (DAAM), a novel probabilistic attention framework that can be used for Parameter-Efficient Fine-tuning (PEFT), and the Density Adaptive Transformer (DAT), designed to enhance…

Machine Learning · Computer Science 2024-10-01 Georgios Ioannides , Aman Chadha , Aaron Elkins

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

Computation and Language · Computer Science 2026-03-27 Yijiong Yu , Jiale Liu , Qingyun Wu , Huazheng Wang , Ji Pei

Slow feature analysis (SFA) is a new technique for extracting slowly varying features from a quickly varying signal. It is shown here that SFA can be applied to nonstationary time series to estimate a single underlying driving force with…

Statistical Mechanics · Physics 2007-05-23 Laurenz Wiskott

The deployment of Large Language Models (LLMs) faces a critical bottleneck when handling lengthy inputs: the prohibitive memory footprint of the Key Value (KV) cache. To address this bottleneck, the token pruning paradigm leverages…

Computation and Language · Computer Science 2026-03-03 Yifei Wang , Yueqi Wang , Zhenrui Yue , Huimin Zeng , Yong Wang , Ismini Lourentzou , Zhengzhong Tu , Xiangxiang Chu , Julian McAuley

In typical Stroop experiments, participants perform better when the colors and words are congruent compared to when they are incongruent or neutral. Paradoxically, in some experimental conditions, neutral trials are faster than congruent…

Neurons and Cognition · Quantitative Biology 2025-06-03 Ahmad Sohrabi , Robert L. West