English
Related papers

Related papers: Dynamic Position Encoding for Transformers

200 papers

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct…

Robotics · Computer Science 2025-03-20 Jianbo Zhao , Taiyu Ban , Zhihao Liu , Hangning Zhou , Xiyang Wang , Qibin Zhou , Hailong Qin , Mu Yang , Lei Liu , Bin Li

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

Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis about how positional information can be stored without…

Computation and Language · Computer Science 2025-01-03 Chunsheng Zuo , Pavel Guerzhoy , Michael Guerzhoy

We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible mapping from the algebraic specification of a domain to an…

Machine Learning · Computer Science 2024-11-01 Konstantinos Kogkalidis , Jean-Philippe Bernardy , Vikas Garg

In transformer architectures, position encoding primarily provides a sense of sequence for input tokens. While the original transformer paper's method has shown satisfactory results in general language processing tasks, there have been new…

Computation and Language · Computer Science 2024-03-26 Eren Unlu

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 adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the…

Computation and Language · Computer Science 2021-08-04 Klaudia Bałazy , Mohammadreza Banaei , Rémi Lebret , Jacek Tabor , Karl Aberer

The attention mechanism is a core primitive in modern large language models (LLMs) and AI more broadly. Since attention by itself is permutation-invariant, position encoding is essential for modeling structured domains such as language.…

Computation and Language · Computer Science 2026-02-05 Songlin Yang , Yikang Shen , Kaiyue Wen , Shawn Tan , Mayank Mishra , Liliang Ren , Rameswar Panda , Yoon Kim

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Xiangxiang Chu , Zhi Tian , Bo Zhang , Xinlong Wang , Chunhua Shen

The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further extend this inquiry by demonstrating that a randomly…

Computation and Language · Computer Science 2023-05-24 Ta-Chung Chi , Ting-Han Fan , Li-Wei Chen , Alexander I. Rudnicky , Peter J. Ramadge

Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…

Computation and Language · Computer Science 2023-11-21 Mingxu Tao , Yansong Feng , Dongyan Zhao

Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting, anomaly detection, and classification. A crucial element of these models is positional…

Machine Learning · Computer Science 2026-05-07 Habib Irani , Vangelis Metsis

The attention mechanism in a Transformer architecture matches key to query based on both content -- the what -- and position in a sequence -- the where. We present an analysis indicating that what and where are entangled in the popular RoPE…

Machine Learning · Computer Science 2025-12-24 Anand Gopalakrishnan , Robert Csordás , Jürgen Schmidhuber , Michael C. Mozer

Directly training a document-to-document (Doc2Doc) neural machine translation (NMT) via Transformer from scratch, especially on small datasets usually fails to converge. Our dedicated probing tasks show that 1) both the absolute position…

Computation and Language · Computer Science 2022-12-13 Yachao Li , Junhui Li , Jing Jiang , Shimin Tao , Hao Yang , Min Zhang

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

In this work, we propose a novel paradigm to encode the position of targets for target tracking in videos using transformers. The proposed paradigm, Dense Spatio-Temporal (DST) position encoding, encodes spatio-temporal position information…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Jinkun Cao , Hao Wu , Kris Kitani

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…

Artificial Intelligence · Computer Science 2025-11-03 Zikang Liu , Longteng Guo , Yepeng Tang , Tongtian Yue , Junxian Cai , Kai Ma , Qingbin Liu , Xi Chen , Jing Liu

In order to preserve word-order information in a non-autoregressive setting, transformer architectures tend to include positional knowledge, by (for instance) adding positional encodings to token embeddings. Several modifications have been…

Computation and Language · Computer Science 2021-09-14 Vinit Ravishankar , Anders Søgaard

Relying entirely on an attention mechanism, the Transformer introduced by Vaswani et al. (2017) achieves state-of-the-art results for machine translation. In contrast to recurrent and convolutional neural networks, it does not explicitly…

Computation and Language · Computer Science 2018-04-16 Peter Shaw , Jakob Uszkoreit , Ashish Vaswani

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this…

Computation and Language · Computer Science 2026-05-12 Yu Wang , Sheng Shen , Rémi Munos , Hongyuan Zhan , Yuandong Tian