English
Related papers

Related papers: Reorganizing attention-space geometry with express…

200 papers

Random-feature-based attention (RFA) is an efficient approximation of softmax attention with linear runtime and space complexity. However, the approximation gap between RFA and conventional softmax attention is not well studied. Built upon…

Machine Learning · Computer Science 2023-02-10 Lin Zheng , Jianbo Yuan , Chong Wang , Lingpeng Kong

Equivariance to symmetries has proven to be a powerful inductive bias in deep learning research. Recent works on mesh processing have concentrated on various kinds of natural symmetries, including translations, rotations, scaling, node…

Machine Learning · Computer Science 2022-08-30 Sourya Basu , Jose Gallego-Posada , Francesco Viganò , James Rowbottom , Taco Cohen

The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Wei Xu , Yi Wan

Attention plays a fundamental role in both natural and artificial intelligence systems. In deep learning, attention-based neural architectures, such as transformer architectures, are widely used to tackle problems in natural language…

Machine Learning · Computer Science 2022-02-18 Pierre Baldi , Roman Vershynin

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and…

Machine Learning · Computer Science 2025-06-05 Marcial Sanchis-Agudo , Yuning Wang , Roger Arnau , Luca Guastoni , Jasmin Lim , Karthik Duraisamy , Ricardo Vinuesa

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

The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality but suffers from large Key-Value (KV) cache memory…

Artificial Intelligence · Computer Science 2025-12-25 Esmail Gumaan

Softmax Self-Attention (SSA) is a key component of Transformer architectures. However, when utilised within skipless architectures, which aim to improve representation learning, recent work has highlighted the inherent instability of SSA…

Machine Learning · Computer Science 2026-02-06 Leo Zhang , James Martens

We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are first combined with a set of learned position biases, the…

Machine Learning · Computer Science 2021-09-23 Shuangfei Zhai , Walter Talbott , Nitish Srivastava , Chen Huang , Hanlin Goh , Ruixiang Zhang , Josh Susskind

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…

Machine Learning · Computer Science 2021-08-12 Yao Zhang , Yunpu Ma , Thomas Seidl , Volker Tresp

We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either suffer from excessively large computational resource…

Computer Vision and Pattern Recognition · Computer Science 2019-12-30 Jonathan Ho , Nal Kalchbrenner , Dirk Weissenborn , Tim Salimans

In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by a considerable margin. This improvement in VQA is often…

Computer Vision and Pattern Recognition · Computer Science 2022-01-12 Ankur Sikarwar , Gabriel Kreiman

Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cross-layer routing. However, standard Attention Residuals still attend over cumulative hidden…

Machine Learning · Computer Science 2026-05-20 Cheng Luo , Zefan Cai , Junjie Hu

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Jiuk Hong , Chaehyeon Lee , Soyoun Bang , Heechul Jung

State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we investigate the global structure of attention scores computed…

Machine Learning · Computer Science 2021-06-17 Srinadh Bhojanapalli , Ayan Chakrabarti , Himanshu Jain , Sanjiv Kumar , Michal Lukasik , Andreas Veit

Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for…

Computation and Language · Computer Science 2026-03-03 Pavlo Vasylenko , Hugo Pitorro , André F. T. Martins , Marcos Treviso

Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant tokens, and probability mass disperses as sequence lengths increase. We tackle these…

Machine Learning · Computer Science 2026-04-17 Xingyue Huang , Xueying Ding , Mingxuan Ju , Yozen Liu , Neil Shah , Tong Zhao

Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, there is a debate on whether attention weights can, in fact,…

Computation and Language · Computer Science 2022-11-16 Bingyang Wen , K. P. Subbalakshmi , Fan Yang

Efficient modeling of long sequences of high-order data requires a more efficient architecture than Transformer. In this paper, we investigate two key aspects of extending linear recurrent models, especially those originally designed for…

Machine Learning · Computer Science 2025-08-19 Yibo Zhong

Multiplicative gating is widely used in neural architectures and has recently been applied to attention layers to improve performance and training stability in large language models. Despite the success of gated attention, the mathematical…

Machine Learning · Computer Science 2026-04-17 Satwik Bathula , Anand A. Joshi