English
Related papers

Related papers: Self-Attention at Constant Cost per Token via Symm…

200 papers

Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and tend to form clusters. While prior work has established clustering behavior for single-head…

Machine Learning · Computer Science 2026-05-11 Ayan Pendharkar

This thesis examines self-attention training through the lens of Optimal Transport (OT) and develops an OT-based alternative for tabular classification. The study tracks intermediate projections of the self-attention layer during training…

Machine Learning · Statistics 2026-02-19 Alessandro Quadrio , Antonio Candelieri

Transformers are strong baselines in both vision and language because self-attention captures long-range dependencies across tokens. However, the cost of self-attention grows quadratically with the number of tokens. Patch pruning mitigates…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Hiroaki Aizawa , Yuki Igaue

Symbolic music generation aims to generate music scores automatically. A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the…

Sound · Computer Science 2022-11-01 Botao Yu , Peiling Lu , Rui Wang , Wei Hu , Xu Tan , Wei Ye , Shikun Zhang , Tao Qin , Tie-Yan Liu

Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset size. Its variants,…

Computation and Language · Computer Science 2025-02-13 Xinglin Wang , Shaoxiong Feng , Yiwei Li , Peiwen Yuan , Yueqi Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

Machine Learning · Computer Science 2020-10-27 Aurko Roy , Mohammad Saffar , Ashish Vaswani , David Grangier

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

Linear attention reduces the quadratic cost of softmax attention to $\mathcal{O}(T)$, but its memory state grows as $\mathcal{O}(T)$ in Frobenius norm, causing progressive interference between stored associations. We introduce…

Machine Learning · Computer Science 2026-05-13 Vishal Pandey , Gopal Singh

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using…

Computation and Language · Computer Science 2019-03-27 Tao Shen , Tianyi Zhou , Guodong Long , Jing Jiang , Chengqi Zhang

Transformers are widely used for their ability to capture data relations in sequence processing, with great success for a wide range of static tasks. However, the computational and memory footprint of their main component, i.e., the Scaled…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Ginés Carreto Picón , Illia Oleksiienko , Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

Transformer-based sequential recommendation (SR) has been booming in recent years, with the self-attention mechanism as its key component. Self-attention has been widely believed to be able to effectively select those informative and…

Information Retrieval · Computer Science 2024-03-19 Peilin Zhou , Qichen Ye , Yueqi Xie , Jingqi Gao , Shoujin Wang , Jae Boum Kim , Chenyu You , Sunghun Kim

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu

The point cloud learning community witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Zhang Cheng , Haocheng Wan , Xinyi Shen , Zizhao Wu

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Time series forecasting is crucial for applications across multiple domains and various scenarios. Although Transformer models have dramatically advanced the landscape of forecasting, their effectiveness remains debated. Recent findings…

Machine Learning · Computer Science 2024-12-24 Dongbin Kim , Jinseong Park , Jaewook Lee , Hoki Kim

We introduce Tangent Attention Fine-Tuning (TAFT), a method for fine-tuning linearized transformers obtained by computing a First-order Taylor Expansion around a pre-trained initialization. We show that the Jacobian-Vector Product resulting…

Machine Learning · Computer Science 2024-05-16 Tian Yu Liu , Aditya Golatkar , Stefano Soatto

Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Hongyi Pan , Emadeldeen Hamdan , Xin Zhu , Ahmet Enis Cetin , Ulas Bagci

This paper reveals that we can interpret the fundamental function of Randomized Time Warping (RTW) as a type of self-attention mechanism, a core technology of Transformers in motion recognition. The self-attention is a mechanism that…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Yutaro Hiraoka , Kazuya Okamura , Kota Suto , Kazuhiro Fukui