English
Related papers

Related papers: HoPE: Hyperbolic Rotary Positional Encoding for St…

200 papers

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

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

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

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

Preventing the performance decay of Transformers on inputs longer than those used for training has been an important challenge in extending the context length of these models. Though the Transformer architecture has fundamentally no limits…

Large language models (LLMs) have revolutionized natural language processing, but their ability to process long sequences is fundamentally limited by the context window size during training. Existing length extrapolation methods often…

Artificial Intelligence · Computer Science 2026-01-13 Nitin Vetcha

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text…

Computer Vision and Pattern Recognition · Computer Science 2024-12-16 Junqi Ge , Ziyi Chen , Jintao Lin , Jinguo Zhu , Xihui Liu , Jifeng Dai , Xizhou Zhu

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

Neural Machine Translation (NMT) models have traditionally used Sinusoidal Positional Embeddings (PEs), which often struggle to capture long-range dependencies and are inefficient for handling extended context or document-level translation…

Computation and Language · Computer Science 2025-02-11 Varun Gumma , Pranjal A. Chitale , Kalika Bali

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

Transformers often struggle to generalize to longer sequences than those seen during training, a limitation known as length extrapolation. Most existing Relative Positional Encoding (RPE) methods attempt to address this by introducing…

Computation and Language · Computer Science 2025-09-23 Ali Veisi , Hamidreza Amirzadeh , Amir Mansourian

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

The transformer architecture has been widely applied to many machine learning tasks. A main bottleneck in the time to perform transformer computations is a task called attention computation. [Alman and Song, NeurIPS 2023] have shown that in…

Machine Learning · Computer Science 2025-05-20 Josh Alman , Zhao Song

Human pose estimation (HPE) usually requires large-scale training data to reach high performance. However, it is rather time-consuming to collect high-quality and fine-grained annotations for human body. To alleviate this issue, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Xixia Xu , Yingguo Gao , Ke Yan , Xue Lin , Qi Zou

The real-world deployment of an autonomous driving system requires its components to run on-board and in real-time, including the motion prediction module that predicts the future trajectories of surrounding traffic participants. Existing…

Computer Vision and Pattern Recognition · Computer Science 2023-10-20 Zhejun Zhang , Alexander Liniger , Christos Sakaridis , Fisher Yu , Luc Van Gool

Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this…

Machine Learning · Computer Science 2021-11-10 Yang Li , Si Si , Gang Li , Cho-Jui Hsieh , Samy Bengio

Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not…

Computation and Language · Computer Science 2023-10-20 Lihu Chen , Gaël Varoquaux , Fabian M. Suchanek

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

Rapid aerodynamic evaluation is crucial for modern vehicle design, yet existing neural operators struggle to capture intricate spatial correlations. We propose the rotary-enhanced transformer operator (RETO), a novel neural solver featuring…

Image and Video Processing · Electrical Eng. & Systems 2026-05-08 Bojun Zhang , Huiyu Yang , Yunpeng Wang , Yuntian Chen , Yuanwei Bin , Rikui Zhang , Jianchun Wang

In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position, our BiPE blends an intra-segment encoding and an…

Machine Learning · Computer Science 2024-06-18 Zhenyu He , Guhao Feng , Shengjie Luo , Kai Yang , Liwei Wang , Jingjing Xu , Zhi Zhang , Hongxia Yang , Di He
‹ Prev 1 4 5 6 7 8 10 Next ›