English
Related papers

Related papers: MrRoPE: Mixed-radix Rotary Position Embedding

200 papers

Embedding techniques have become essential components of large databases in the deep learning era. By encoding discrete entities, such as words, items, or graph nodes, into continuous vector spaces, embeddings facilitate more efficient…

Information Retrieval · Computer Science 2024-10-18 Shiwei Li , Zhuoqi Hu , Xing Tang , Haozhao Wang , Shijie Xu , Weihong Luo , Yuhua Li , Xiuqiang He , Ruixuan Li

The performance of human pose estimation depends on the spatial accuracy of keypoint localization. Most existing methods pursue the spatial accuracy through learning the high-resolution (HR) representation from input images. By the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-08 Hanbin Dai , Hailin Shi , Wu Liu , Linfang Wang , Yinglu Liu , Tao Mei

Standard Vision Transformers flatten 2D images into 1D sequences, disrupting the natural spatial topology. While Rotary Positional Embedding (RoPE) excels in 1D, it inherits this limitation, often treating spatially distant patches (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Yupu Yao , Bowen Yang

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based…

Machine Learning · Computer Science 2022-10-31 Shengjie Luo , Shanda Li , Shuxin Zheng , Tie-Yan Liu , Liwei Wang , Di He

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

Linear position interpolation helps pre-trained models using rotary position embeddings (RoPE) to extrapolate to longer sequence lengths. We propose using linear position interpolation to extend the extrapolation range of models using…

Computation and Language · Computer Science 2023-10-23 Faisal Al-Khateeb , Nolan Dey , Daria Soboleva , Joel Hestness

We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach…

Computation and Language · Computer Science 2021-01-25 Zehui Lin , Xiao Pan , Mingxuan Wang , Xipeng Qiu , Jiangtao Feng , Hao Zhou , Lei Li

Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to capture the ordering of the time series data. The efficacy…

Machine Learning · Computer Science 2024-02-21 Navid Mohammadi Foumani , Chang Wei Tan , Geoffrey I. Webb , Mahsa Salehi

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

Representation learning on multi-omics data is challenging due to extreme dimensionality, modality heterogeneity, and cohort-specific batch effects. While pre-trained transformer backbones have shown broad generalization capabilities in…

Machine Learning · Computer Science 2025-11-27 Audrey Pei-Hsuan Chen

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Computation and Language · Computer Science 2019-10-01 Inigo Jauregi Unanue , Ehsan Zare Borzeshi , Massimo Piccardi

Interpreting the information encoded in model weights remains a fundamental challenge in mechanistic interpretability. In this work, we introduce ROTATE (Rotation-Optimized Token Alignment in weighT spacE), a data-free method requiring no…

Computation and Language · Computer Science 2026-04-08 Asaf Avrahamy , Yoav Gur-Arieh , Mor Geva

Multi-relational learning has received lots of attention from researchers in various research communities. Most existing methods either suffer from superlinear per-iteration cost, or are sensitive to the given ranks. To address both issues,…

Machine Learning · Computer Science 2016-01-19 Fanhua Shang , James Cheng , Hong Cheng

Positional embeddings (PE) play a crucial role in Vision Transformers (ViTs) by providing spatial information otherwise lost due to the permutation invariant nature of self attention. While absolute positional embeddings (APE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Md Abtahi Majeed Chowdhury , Md Rifat Ur Rahman , Akil Ahmad Taki

Length generalization is the ability of language models to maintain performance on inputs longer than those seen during pretraining. In this work, we introduce a simple yet powerful position encoding (PE) strategy, Random Float Sampling…

Machine Learning · Computer Science 2026-02-17 Atsushi Shimizu , Shohei Taniguchi , Yutaka Matsuo

Retrieval-Augmented Generation (RAG) systems enhance text generation by incorporating external knowledge but often struggle when retrieving context across different text modalities due to semantic gaps. We introduce a generalized…

Machine Learning · Computer Science 2024-11-01 Arihan Yadav , Alan McMillan

In this paper, we present MixRep, a simple and effective data augmentation strategy based on mixup for low-resource ASR. MixRep interpolates the feature dimensions of hidden representations in the neural network that can be applied to both…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-19 Jiamin Xie , John H. L. Hansen

Length extrapolation has attracted considerable attention recently since it allows transformers to be tested on longer sequences than those used in training. Previous research has shown that this property can be attained by using carefully…

Computation and Language · Computer Science 2023-12-20 Zhen Qin , Yiran Zhong , Hui Deng

Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents, ranging from simple keywords to complex compositional instructions. While Multimodal Large Language Models (MLLMs) possess strong…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Xiangzhao Hao , Shijie Wang , Tianyu Yang , Tianyue Wang , Haiyun Guo , Jinqiao Wang

Although large language models (LLMs) have achieved significant progress in handling long-context inputs, they still suffer from the ``lost-in-the-middle'' problem, where crucial information in the middle of the context is often…

Computation and Language · Computer Science 2025-03-07 Zhenghua Wang , Yiran Ding , Changze Lv , Zhibo Xu , Tianlong Li , Tianyuan Shi , Xiaoqing Zheng , Xuanjing Huang
‹ Prev 1 3 4 5 6 7 10 Next ›