English
Related papers

Related papers: Relative Positional Encoding for Transformers with…

200 papers

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

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

We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find…

Positional encoding (PE) is a core architectural component of Transformers, yet its impact on the Transformer's generalization and robustness remains unclear. In this work, we provide the first generalization analysis for a single-layer…

Machine Learning · Statistics 2026-03-25 Weiyi He , Yue Xing

Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-view transformers must use camera geometry…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Ruilong Li , Brent Yi , Junchen Liu , Hang Gao , Yi Ma , Angjoo Kanazawa

Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce…

Computation and Language · Computer Science 2025-08-22 Jiajun Zhu , Peihao Wang , Ruisi Cai , Jason D. Lee , Pan Li , Zhangyang Wang

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded…

Machine Learning · Computer Science 2025-11-18 Felipe Urrutia , Jorge Salas , Alexander Kozachinskiy , Cristian Buc Calderon , Hector Pasten , Cristobal Rojas

In this study, we investigate the impact of positional encoding (PE) on source separation performance and the generalization ability to long sequences (length extrapolation) in Transformer-based time-frequency (TF) domain dual-path models.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-03 Kohei Saijo , Tetsuji Ogawa

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

While music remains a challenging domain for generative models like Transformers, recent progress has been made by exploiting suitable musically-informed priors. One technique to leverage information about musical structure in Transformers…

Sound · Computer Science 2025-02-18 Manvi Agarwal , Changhong Wang , Gael Richard

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various…

Computation and Language · Computer Science 2023-11-09 Jianlin Su , Yu Lu , Shengfeng Pan , Ahmed Murtadha , Bo Wen , Yunfeng Liu

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term…

Computation and Language · Computer Science 2024-12-06 Yuhan Chen , Ang Lv , Jian Luan , Bin Wang , Wei Liu

Rotary Positional Encodings (RoPE) have emerged as a highly effective technique for one-dimensional sequences in Natural Language Processing spurring recent progress towards generalizing RoPE to higher-dimensional data such as images and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Chase van de Geijn , Timo Lüddecke , Polina Turishcheva , Alexander S. Ecker

This study reports an unintuitive finding that positional encoding enhances learning of recurrent neural networks (RNNs). Positional encoding is a high-dimensional representation of time indices on input data. Most famously, positional…

Machine Learning · Computer Science 2024-11-28 Takashi Morita

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

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

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of positional encoding:…

Machine Learning · Computer Science 2024-08-26 Mitchell Black , Zhengchao Wan , Gal Mishne , Amir Nayyeri , Yusu Wang

Vision transformers have demonstrated significant advantages in computer vision tasks due to their ability to capture long-range dependencies and contextual relationships through self-attention. However, existing position encoding…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Xi Chen , Shiyang Zhou , Muqi Huang , Jiaxu Feng , Yun Xiong , Kun Zhou , Biao Yang , Yuhui Zhang , Huishuai Bao , Sijia Peng , Chuan Li , Feng Shi

Length generalization, the ability to generalize from small training context sizes to larger ones, is a critical challenge in the development of Transformer-based language models. Positional encoding (PE) has been identified as a major…

Computation and Language · Computer Science 2023-11-08 Amirhossein Kazemnejad , Inkit Padhi , Karthikeyan Natesan Ramamurthy , Payel Das , Siva Reddy

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

Computation and Language · Computer Science 2024-05-31 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar