English
Related papers

Related papers: Fourier Position Embedding: Enhancing Attention's …

200 papers

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Machine Learning · Computer Science 2026-05-12 Riccardo Ali , Alessio Borgi , Christopher Irwin , Mario Severino , Pietro Liò

So far, expensive finetuning beyond the pretraining sequence length has been a requirement for effectively extending the context of language models (LM). In this work, we break this key bottleneck by Dropping the Positional Embeddings of…

Computation and Language · Computer Science 2025-12-16 Yoav Gelberg , Koshi Eguchi , Takuya Akiba , Edoardo Cetin

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

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

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

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

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

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

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

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

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

Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in specific layers, the effect of varying the fraction of…

Machine Learning · Computer Science 2026-03-13 Mohammad Aflah Khan , Krishna P. Gummadi , Manish Gupta , Abhilasha Ravichander

Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on…

Computation and Language · Computer Science 2025-05-20 Wenqiao Zhu , Chao Xu , Lulu Wang , Jun Wu

We propose a new class of linear Transformers called FourierLearner-Transformers (FLTs), which incorporate a wide range of relative positional encoding mechanisms (RPEs). These include regular RPE techniques applied for sequential data, as…

Transformer-based Large Language Models (LLMs) rely on positional encodings to provide sequence position information to their attention mechanism. Rotary Positional Encodings (RoPE), which encode relative position by rotating queries and…

Computation and Language · Computer Science 2025-08-25 André Jonasson

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

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

Positional Encodings (PEs) are a critical component of Transformer-based Large Language Models (LLMs), providing the attention mechanism with important sequence-position information. One of the most popular types of encoding used today in…

Computation and Language · Computer Science 2025-05-14 Federico Barbero , Alex Vitvitskyi , Christos Perivolaropoulos , Razvan Pascanu , Petar Veličković

Extending the context window support of large language models (LLMs) is crucial for tasks with long-distance dependencies. RoPE-based interpolation and extrapolation methods, such as linear scaling and frequency-aware schemes, enable longer…

Machine Learning · Computer Science 2025-10-02 Ye Qiao , Haocheng Xu , Xiaofan Zhang , Sitao Huang