English
Related papers

Related papers: PaTH Attention: Position Encoding via Accumulating…

200 papers

Operator learning for Partial Differential Equations (PDEs) is rapidly emerging as a promising approach for surrogate modeling of intricate systems. Transformers with the self-attention mechanism$\unicode{x2013}$a powerful tool originally…

Machine Learning · Computer Science 2024-05-17 Junfeng Chen , Kailiang Wu

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

Computation and Language · Computer Science 2026-05-29 Pierre-Antoine Lequeu , Camille Barboule , Benjamin Piwowarski

Positional encoding mechanisms enable Transformers to model sequential structure and long-range dependencies in text. While absolute positional encodings struggle with extrapolation to longer sequences due to fixed positional…

Computation and Language · Computer Science 2025-09-09 Chang Dai , Hongyu Shan , Mingyang Song , Di Liang

Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window, primarily due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). Recent studies…

Computation and Language · Computer Science 2025-08-06 Sikui Zhang , Guangze Gao , Ziyun Gan , Chunfeng Yuan , Zefeng Lin , Houwen Peng , Bing Li , Weiming Hu

Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent methods emphasize…

Machine Learning · Computer Science 2025-11-18 Chase van de Geijn , Ayush Paliwal , Timo Lüddecke , Alexander S. Ecker

Long-context large language models (LLMs) have achieved remarkable advancements, driven by techniques like Rotary Position Embedding (RoPE) (Su et al., 2023) and its extensions (Chen et al., 2023; Liu et al., 2024c; Peng et al., 2023). By…

Computation and Language · Computer Science 2025-10-24 Bowen Yang , Bharat Venkitesh , Dwarak Talupuru , Hangyu Lin , David Cairuz , Phil Blunsom , Acyr Locatelli

Large Language Models (LLMs) are known to have limited extrapolation ability beyond their pre-trained context window, constraining their application in downstream tasks with lengthy inputs. Recent studies have sought to extend LLMs' context…

Computation and Language · Computer Science 2024-01-17 Yikai Zhang , Junlong Li , Pengfei Liu

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer…

Sound · Computer Science 2021-07-14 Shengqiang Li , Menglong Xu , Xiao-Lei Zhang

Tensor Attention extends traditional attention mechanisms by capturing high-order correlations across multiple modalities, addressing the limitations of classical matrix-based attention. Meanwhile, Rotary Position Embedding…

Machine Learning · Computer Science 2024-12-25 Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song , Mingda Wan

In Transformer-based architectures, the attention mechanism is inherently permutation-invariant with respect to the input sequence's tokens. To impose sequential order, token positions are typically encoded using a scheme with either fixed…

Machine Learning · Computer Science 2023-10-31 Giorgio Angelotti

The transformer architecture has been widely applied to many machine learning tasks. A main bottleneck in the time to perform transformer computations is a task called attention computation. [Alman and Song, NeurIPS 2023] have shown that in…

Machine Learning · Computer Science 2025-05-20 Josh Alman , Zhao Song

The Transformer architecture has revolutionized various regions since it was proposed, and its effectiveness largely depends on the ability to encode positional information. Traditional position encoding methods exhibit significant…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Hao Yu , Tangyu Jiang , Shuning Jia , Shannan Yan , Shunning Liu , Haolong Qian , Guanghao Li , Shuting Dong , Huaisong Zhang , Chun Yuan

Recurrent models have been dominating the field of neural machine translation (NMT) for the past few years. Transformers \citep{vaswani2017attention}, have radically changed it by proposing a novel architecture that relies on a feed-forward…

Computation and Language · Computer Science 2022-10-25 Joyce Zheng , Mehdi Rezagholizadeh , Peyman Passban

Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de facto standard due to its relative positional encoding…

Computation and Language · Computer Science 2024-11-27 Haonan Wang , Qian Liu , Chao Du , Tongyao Zhu , Cunxiao Du , Kenji Kawaguchi , Tianyu Pang

Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional encoding (APE) and relative positional encoding (RPE) to…

Computation and Language · Computer Science 2024-11-06 Chuanyang Zheng , Yihang Gao , Han Shi , Minbin Huang , Jingyao Li , Jing Xiong , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Machine Learning · Computer Science 2021-11-04 Shengjie Luo , Shanda Li , Tianle Cai , Di He , Dinglan Peng , Shuxin Zheng , Guolin Ke , Liwei Wang , Tie-Yan Liu

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Machine Learning · Computer Science 2021-02-26 Yujing Wang , Yaming Yang , Jiangang Bai , Mingliang Zhang , Jing Bai , Jing Yu , Ce Zhang , Gao Huang , Yunhai Tong

In the realm of large-scale language models, a significant challenge arises when extrapolating sequences beyond the maximum allowable length. This is because the model's position embedding mechanisms are limited to positions encountered…

Computation and Language · Computer Science 2025-02-05 Yui Oka , Taku Hasegawa , Kyosuke Nishida , Kuniko Saito

We present PAT, a transformer-based network that learns complex temporal co-occurrence action dependencies in a video by exploiting multi-scale temporal features. In existing methods, the self-attention mechanism in transformers loses the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Faegheh Sardari , Armin Mustafa , Philip J. B. Jackson , Adrian Hilton

There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in…

Computation and Language · Computer Science 2024-05-09 Arpit Aggarwal