English
Related papers

Related papers: Memorization Capacity of Multi-Head Attention in T…

200 papers

Transformers have emerged as a powerful neural network architecture capable of tackling a wide range of learning tasks. In this work, we provide a theoretical analysis of their ability to automatically extract structure from data in an…

Machine Learning · Statistics 2025-10-29 Rodrigo Maulen-Soto , Pierre Marion , Claire Boyer

Sequence models face a fundamental tradeoff between memory capacity and computational efficiency. Transformers achieve expressive context modeling at quadratic cost, while linear attention and state-space models run in linear time by…

Machine Learning · Computer Science 2026-05-11 Yaxita Amin , Helen Zichen Li , Mengfan Zhang , Samet Ayhan

Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers with hardmax self-attention and normalization sublayers as…

Computation and Language · Computer Science 2026-05-14 Albert Alcalde , Giovanni Fantuzzi , Enrique Zuazua

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that transformers can implement gradient descent as an in-context…

Machine Learning · Computer Science 2024-08-09 Xingwu Chen , Lei Zhao , Difan Zou

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

Computation and Language · Computer Science 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Computation and Language · Computer Science 2025-02-07 Zifan He , Yingqi Cao , Zongyue Qin , Neha Prakriya , Yizhou Sun , Jason Cong

Transformer-based models have become ubiquitous in natural language processing thanks to their large capacity, innate parallelism and high performance. The contextualizing component of a Transformer block is the $\textit{pairwise…

Machine Learning · Computer Science 2020-06-08 Ankit Gupta , Jonathan Berant

Transformer models gain popularity because of their superior inference accuracy and inference throughput. However, the transformer is computation-intensive, causing a long inference time. The existing works on transformer inference…

Performance · Computer Science 2023-04-19 Yuan Feng , Hyeran Jeon , Filip Blagojevic , Cyril Guyot , Qing Li , Dong Li

Multi-head attention layers, as used in the Transformer neural sequence model, are a powerful alternative to RNNs for moving information across and between sequences. While training these layers is generally fast and simple, due to…

Neural and Evolutionary Computing · Computer Science 2019-11-07 Noam Shazeer

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

Transformers are emerging as the new workhorse of NLP, showing great success across tasks. Unlike LSTMs, transformers process input sequences entirely through self-attention. Previous work has suggested that the computational capabilities…

Computation and Language · Computer Science 2021-06-28 Michael Hahn

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

As the demand for processing extended textual data grows, the ability to handle long-range dependencies and maintain computational efficiency is more critical than ever. One of the key issues for long-sequence modeling using attention-based…

Computation and Language · Computer Science 2025-05-26 Aosong Feng , Rex Ying , Leandros Tassiulas

Large Language Models (LLMs), trained on massive corpora with billions of parameters, show unprecedented performance in various fields. Though surprised by their excellent performances, researchers also noticed some special behaviors of…

Computation and Language · Computer Science 2024-06-05 Bowen Chen , Namgi Han , Yusuke Miyao

Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is spread across multiple layers and model components,…

Computation and Language · Computer Science 2024-04-01 Niklas Stoehr , Mitchell Gordon , Chiyuan Zhang , Owen Lewis

Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite…

Computation and Language · Computer Science 2022-03-28 Pedro Henrique Martins , Zita Marinho , André F. T. Martins

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Computation and Language · Computer Science 2020-12-03 Iz Beltagy , Matthew E. Peters , Arman Cohan

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang
‹ Prev 1 3 4 5 6 7 10 Next ›