English
Related papers

Related papers: A Simple and Effective Positional Encoding for Tra…

200 papers

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…

Computation and Language · Computer Science 2021-09-28 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

Pre-trained language models demonstrate general intelligence and common sense, but long inputs quickly become a bottleneck for memorizing information at inference time. We resurface a simple method, Memorizing Transformers (Wu et al.,…

Machine Learning · Computer Science 2024-06-05 Phoebe Klett , Thomas Ahle

Transformer-based neural networks have surpassed promising performance on many biomedical image segmentation tasks due to a better global information modeling from the self-attention mechanism. However, most methods are still designed for…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Zheyuan Zhang , Ulas Bagci

We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches. Our framework provides a flexible mapping from the algebraic specification of a domain to an…

Machine Learning · Computer Science 2024-11-01 Konstantinos Kogkalidis , Jean-Philippe Bernardy , Vikas Garg

Transformer-based image denoising methods have achieved encouraging results in the past year. However, it must uses linear operations to model long-range dependencies, which greatly increases model inference time and consumes GPU storage…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Juncheng Li , Bodong Cheng , Ying Chen , Guangwei Gao , Tieyong Zeng

Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights DO capture accurate…

Computation and Language · Computer Science 2020-12-04 Yun Chen , Yang Liu , Guanhua Chen , Xin Jiang , Qun Liu

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Zizheng Pan , Bohan Zhuang , Haoyu He , Jing Liu , Jianfei Cai

Transformers are powerful for sequence modeling. Nearly all state-of-the-art language models and pre-trained language models are based on the Transformer architecture. However, it distinguishes sequential tokens only with the token position…

Computation and Language · Computer Science 2020-12-17 He Bai , Peng Shi , Jimmy Lin , Yuqing Xie , Luchen Tan , Kun Xiong , Wen Gao , Ming Li

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive theoretical understanding of how attention masks and…

Machine Learning · Computer Science 2025-08-12 Xinyi Wu , Yifei Wang , Stefanie Jegelka , Ali Jadbabaie

Modular exponentiation is crucial to number theory and cryptography, yet remains largely unexplored from a mechanistic interpretability standpoint. We train a 4-layer encoder-decoder Transformer model to perform this operation and…

Machine Learning · Computer Science 2025-10-24 David Demitri Africa , Sara M. Kapoor , Theo Simon Sorg , Challenger Mishra

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Tommie Kerssies , Niccolò Cavagnero , Alexander Hermans , Narges Norouzi , Giuseppe Averta , Bastian Leibe , Gijs Dubbelman , Daan de Geus

Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into…

Sound · Computer Science 2025-02-11 Adam Stooke , Rohit Prabhavalkar , Khe Chai Sim , Pedro Moreno Mengibar

Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Yangyang Xu , Yibo Yang , Lefei Zhang

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…

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

Computation and Language · Computer Science 2016-09-28 Lei Yu , Jan Buys , Phil Blunsom

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

Computation and Language · Computer Science 2023-05-12 Yanyang Li , Ye Lin , Tong Xiao , Jingbo Zhu

Medical image segmentation is crucial for the development of computer-aided diagnostic and therapeutic systems, but still faces numerous difficulties. In recent years, the commonly used encoder-decoder architecture based on CNNs has been…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Davoud Saadati , Omid Nejati Manzari , Sattar Mirzakuchaki

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

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Sina Hajimiri , Farzad Beizaee , Fereshteh Shakeri , Christian Desrosiers , Ismail Ben Ayed , Jose Dolz

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment…

Computation and Language · Computer Science 2021-09-14 Javier Ferrando , Marta R. Costa-jussà