English
Related papers

Related papers: Dynamic Position Encoding for Transformers

200 papers

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

This paper studies how Transformer models with Rotary Position Embeddings (RoPE) develop emergent, wavelet-like properties that compensate for the positional encoding's theoretical limitations. Through an analysis spanning model scales,…

Machine Learning · Computer Science 2025-06-06 Valeria Ruscio , Umberto Nanni , Fabrizio Silvestri

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

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

Transformer architecture has enabled recent progress in speech enhancement. Since Transformers are position-agostic, positional encoding is the de facto standard component used to enable Transformers to distinguish the order of elements in…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Qiquan Zhang , Meng Ge , Hongxu Zhu , Eliathamby Ambikairajah , Qi Song , Zhaoheng Ni , Haizhou Li

Auto-regressive neural sequence models have been shown to be effective across text generation tasks. However, their left-to-right decoding order prevents generation from being parallelized. Insertion Transformer (Stern et al., 2019) is an…

Computation and Language · Computer Science 2023-02-01 Zhisong Zhang , Yizhe Zhang , Bill Dolan

Position encoding is the primary mechanism which induces notion of sequential order for input tokens in transformer architectures. Even though this formulation in the original transformer paper has yielded plausible performance for general…

Computation and Language · Computer Science 2023-10-10 Eren Unlu

We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing…

Machine Learning · Computer Science 2024-05-17 Tsuyoshi Idé , Jokin Labaien , Pin-Yu Chen

Positional encoding is a vital component of Transformer architectures, enabling models to incorporate sequence order into self-attention mechanisms. Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their…

Computation and Language · Computer Science 2025-08-01 Ali Veisi , Delaram Fartoot , Hamidreza Amirzadeh

Sequential word order is important when processing text. Currently, neural networks (NNs) address this by modeling word position using position embeddings. The problem is that position embeddings capture the position of individual words,…

Computation and Language · Computer Science 2020-06-30 Benyou Wang , Donghao Zhao , Christina Lioma , Qiuchi Li , Peng Zhang , Jakob Grue Simonsen

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Transformer language models encode the notion of word order using positional information. Most commonly, this positional information is represented by absolute position embeddings (APEs), that are learned from the pretraining data. However,…

Computation and Language · Computer Science 2022-10-25 Koustuv Sinha , Amirhossein Kazemnejad , Siva Reddy , Joelle Pineau , Dieuwke Hupkes , Adina Williams

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

We conducted empirical experiments to assess the transferability of a light curve transformer to datasets with different cadences and magnitude distributions using various positional encodings (PEs). We proposed a new approach to…

Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations, while in linear transformers, order is handled via…

Computation and Language · Computer Science 2026-04-27 Sajad Movahedi , Timur Carstensen , Arshia Afzal , Frank Hutter , Antonio Orvieto , Volkan Cevher

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

Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Sophie Ostmeier , Brian Axelrod , Maya Varma , Michael E. Moseley , Akshay Chaudhari , Curtis Langlotz

Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…

Graphics · Computer Science 2026-02-06 Aryan Mikaeili , Or Patashnik , Andrea Tagliasacchi , Daniel Cohen-Or , Ali Mahdavi-Amiri

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition…

Computation and Language · Computer Science 2021-03-16 Guolin Ke , Di He , Tie-Yan Liu

Graph Transformers (GTs) facilitate the comprehension of graph-structured data by calculating the self-attention of node pairs without considering node position information. To address this limitation, we introduce an innovative and…

Machine Learning · Computer Science 2023-12-12 Kushal Bose , Swagatam Das