English
Related papers

Related papers: Exploring Transformer Extrapolation

200 papers

Transformer network architecture has proven effective in speech enhancement. However, as its core module, self-attention suffers from quadratic complexity, making it infeasible for training on long speech utterances. In practical scenarios,…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-10 Qiquan Zhang , Hongxu Zhu , Xinyuan Qian , Eliathamby Ambikairajah , Haizhou Li

Looped Transformers provide advantages in parameter efficiency, computational capabilities, and generalization for reasoning tasks. However, their expressive power regarding function approximation remains underexplored. In this paper, we…

Machine Learning · Computer Science 2025-06-06 Kevin Xu , Issei Sato

A recent variation of Transformer, Performer, scales Transformer to longer sequences with a linear attention mechanism. However, it is not compatible with relative position encoding, which has advantages over absolute position encoding. In…

Computation and Language · Computer Science 2021-09-09 Peng Chen

The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by…

Computation and Language · Computer Science 2024-10-11 Chuanyang Zheng , Yihang Gao , Han Shi , Jing Xiong , Jiankai Sun , Jingyao Li , Minbin Huang , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

Neural networks are surprisingly good at interpolating and perform remarkably well when the training set examples resemble those in the test set. However, they are often unable to extrapolate patterns beyond the seen data, even when the…

Machine Learning · Computer Science 2020-04-23 Yann Dubois , Gautier Dagan , Dieuwke Hupkes , Elia Bruni

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term…

Computation and Language · Computer Science 2024-12-06 Yuhan Chen , Ang Lv , Jian Luan , Bin Wang , Wei Liu

The Transformer model has a tendency to overfit various aspects of the training data, such as the overall sequence length. We study elementary string edit functions using a defined set of error indicators to interpret the behaviour of the…

Machine Learning · Computer Science 2024-10-18 Patrik Zavoral , Dušan Variš , Ondřej Bojar

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

Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily…

Machine Learning · Computer Science 2026-02-23 M. Reza Ebrahimi , Michaël Defferrard , Sunny Panchal , Roland Memisevic

In this paper, we investigate the inherent capabilities of transformer models in learning arithmetic algorithms, such as addition and parity. Through experiments and attention analysis, we identify a number of crucial factors for achieving…

Machine Learning · Computer Science 2024-05-13 Shaoxiong Duan , Yining Shi , Wei Xu

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

Relative position encoding (RPE) is important for transformer to capture sequence ordering of input tokens. General efficacy has been proven in natural language processing. However, in computer vision, its efficacy is not well studied and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 Kan Wu , Houwen Peng , Minghao Chen , Jianlong Fu , Hongyang Chao

Rotary Position Embeddings (RoPE) have been shown to effectively encode positional information in transformer-based language models. However, these models fail to generalize past the sequence length they were trained on. We present YaRN…

Computation and Language · Computer Science 2026-02-10 Bowen Peng , Jeffrey Quesnelle , Honglu Fan , Enrico Shippole

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

Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement…

Machine Learning · Computer Science 2023-01-24 Shengchao Hu , Li Shen , Ya Zhang , Yixin Chen , Dacheng Tao

Large Language Models (LLMs) often struggle to process and generate coherent context when the number of input tokens exceeds the pre-trained length. Recent advancements in long-context extension have significantly expanded the context…

Computation and Language · Computer Science 2025-04-29 Yi Lu , Wanxu Zhao , Xin Zhou , Chenxin An , Chenglong Wang , Shuo Li , Yuming Yang , Jun Zhao , Tao Ji , Tao Gui , Qi Zhang , Xuanjing Huang

Without positional information, attention-based Transformer neural networks are permutation-invariant. Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information. Absolute…

Machine Learning · Computer Science 2021-11-10 Tatiana Likhomanenko , Qiantong Xu , Gabriel Synnaeve , Ronan Collobert , Alex Rogozhnikov

Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transformer variant named RegularGPT. With its novel combination of…

Computation and Language · Computer Science 2023-05-09 Ta-Chung Chi , Ting-Han Fan , Alexander I. Rudnicky , Peter J. Ramadge

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

Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks. This survey explores how transformers are used in…

Machine Learning · Computer Science 2023-07-13 Pranav Agarwal , Aamer Abdul Rahman , Pierre-Luc St-Charles , Simon J. D. Prince , Samira Ebrahimi Kahou