English
Related papers

Related papers: Rotary Offset Features in Large Language Models

200 papers

Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown promising results in extending the context length of language models. However, understanding how position embedding can capture longer-range contextual…

Computation and Language · Computer Science 2024-10-22 Xiangyu Hong , Che Jiang , Biqing Qi , Fandong Meng , Mo Yu , Bowen Zhou , Jie Zhou

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

Position embedding is a core component of current Large Language Models (LLMs). Rotary position embedding (RoPE), a technique that encodes the position information with a rotation matrix, has been the de facto choice for position embedding…

Computation and Language · Computer Science 2024-05-24 Xin Men , Mingyu Xu , Bingning Wang , Qingyu Zhang , Hongyu Lin , Xianpei Han , Weipeng Chen

Multimodal position encoding is essential for vision-language models, yet there has been little systematic investigation into multimodal position encoding. We conduct a comprehensive analysis of multimodal Rotary Positional Embedding (RoPE)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Jie Huang , Xuejing Liu , Sibo Song , Ruibing Hou , Hong Chang , Junyang Lin , Shuai Bai

Rotary positional embeddings (RoPE) are widely used in large language models to encode token positions through multiplicative rotations, yet their behavior at long context lengths remains poorly characterized. In this work, we reinterpret…

Machine Learning · Computer Science 2026-02-12 Feilong Liu

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

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

Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show that these concentrated massive values consistently emerge in specific regions of attention queries (Q) and keys (K)…

Computation and Language · Computer Science 2025-05-22 Mingyu Jin , Kai Mei , Wujiang Xu , Mingjie Sun , Ruixiang Tang , Mengnan Du , Zirui Liu , Yongfeng Zhang

Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the $\Delta$-th sub-diagonal for some offset $\Delta$. These patterns play a key role in passing information across tokens. But…

Machine Learning · Computer Science 2026-01-29 Yuan Cheng , Fengzhuo Zhang , Yunlong Hou , Cunxiao Du , Chao Du , Tianyu Pang , Aixin Sun , Zhuoran Yang

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…

Enabling LLMs to handle lengthy context is currently a research hotspot. Most LLMs are built upon rotary position embedding (RoPE), a popular position encoding method. Therefore, a prominent path is to extrapolate the RoPE trained on…

Computation and Language · Computer Science 2024-12-13 Meizhi Zhong , Chen Zhang , Yikun Lei , Xikai Liu , Yan Gao , Yao Hu , Kehai Chen , Min 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 widely adopted in large language models (LLMs) due to its efficient encoding of relative positions with strong extrapolation capabilities. However, while its application in higher-dimensional input…

Machine Learning · Computer Science 2025-07-16 Haiping Liu , Lijing Lin , Jingyuan Sun , Zhegong Shangguan , Mauricio A. Alvarez , Hongpeng Zhou

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

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

Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs). While various methods have been proposed to adapt RoPE to longer contexts, their guiding principles generally fall into two…

Computation and Language · Computer Science 2026-02-06 Haoran Li , Sucheng Ren , Alan Yuille , Feng Wang

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

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

This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with…

Computation and Language · Computer Science 2024-09-05 Suyuchen Wang , Ivan Kobyzev , Peng Lu , Mehdi Rezagholizadeh , Bang Liu

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Chengcheng Wang , Jianyuan Guo , Hongguang Li , Yuchuan Tian , Ying Nie , Chang Xu , Kai Han