English
Related papers

Related papers: Reducing the Transformer Architecture to a Minimum

200 papers

Large language models (LLMs) demonstrate an impressive ability to utilise information within the context of their input sequences to appropriately respond to data unseen by the LLM during its training procedure. This ability is known as…

Neural and Evolutionary Computing · Computer Science 2025-08-05 Thomas F Burns , Tomoki Fukai , Christopher J Earls

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Leijie Wu , Song Guo , Yaohong Ding , Junxiao Wang , Wenchao Xu , Richard Yida Xu , Jie Zhang

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

Attention is a cornerstone of human cognition that facilitates the efficient extraction of information in everyday life. Recent developments in artificial intelligence like the Transformer architecture also incorporate the idea of attention…

Other Quantitative Biology · Quantitative Biology 2024-07-03 Minglu Zhao , Dehong Xu , Tao Gao

Transformers have established themselves as the leading neural network model in natural language processing and are increasingly foundational in various domains. In vision, the MLP-Mixer model has demonstrated competitive performance,…

Machine Learning · Computer Science 2024-06-19 Ryo Karakida , Toshihiro Ota , Masato Taki

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we…

Computation and Language · Computer Science 2024-12-24 Prateek Verma , Mert Pilanci

The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform…

Machine Learning · Computer Science 2024-04-17 Xuezhe Ma , Xiaomeng Yang , Wenhan Xiong , Beidi Chen , Lili Yu , Hao Zhang , Jonathan May , Luke Zettlemoyer , Omer Levy , Chunting Zhou

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Machine Learning · Computer Science 2023-05-09 Riccardo Ughi , Eugenio Lomurno , Matteo Matteucci

The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention…

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either…

Computation and Language · Computer Science 2023-07-19 Amine Abdaoui , Sourav Dutta

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking…

Machine Learning · Computer Science 2024-12-12 Erwan Fagnou , Paul Caillon , Blaise Delattre , Alexandre Allauzen

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Christian Bohn , Thomas Kurbiel , Klaus Friedrichs , Hasan Tercan , Tobias Meisen

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

We present a novel non attention based architecture for large language models (LLMs) that efficiently handles very long context windows, on the order of hundreds of thousands to potentially millions of tokens. Unlike traditional Transformer…

Machine Learning · Computer Science 2025-06-04 Andrew Kiruluta , Preethi Raju , Priscilla Burity

Transformers have achieved great success in machine translation, but transformer-based NMT models often require millions of bilingual parallel corpus for training. In this paper, we propose a novel architecture named as attention link (AL)…

Computation and Language · Computer Science 2023-02-02 Zeping Min

While attention has been empirically shown to improve model performance, it lacks a rigorous mathematical justification. This short paper establishes a novel connection between attention mechanisms and multinomial regression. Specifically,…

Machine Learning · Computer Science 2025-10-28 Jonas A. Actor , Anthony Gruber , Eric C. Cyr

Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency (mainly in terms of memory) on the sequence length due to…