English
Related papers

Related papers: TRA: Better Length Generalisation with Threshold R…

200 papers

Despite their dominance in modern DL and, especially, NLP domains, transformer architectures exhibit sub-optimal performance on long-range tasks compared to recent layers that are specifically designed for this purpose. In this work,…

Machine Learning · Computer Science 2023-11-29 Itamar Zimerman , Lior Wolf

Can a transformer learn which attention entries matter during training? In principle, yes: attention distributions are highly concentrated, and a small gate network can identify the important entries post-hoc with near-perfect accuracy. In…

Machine Learning · Computer Science 2026-03-04 Keston Aquino-Michaels

Softmax self-attention often assigns disproportionate weight to semantically uninformative tokens such as special tokens and punctuation, a phenomenon known as attention noise. While recent methods like Cog Attention and the Differential…

Computation and Language · Computer Science 2025-08-27 Ivan Kobyzev , Abbas Ghaddar , Dingtao Hu , Boxing Chen

The Transformer architecture has become widely adopted due to its demonstrated success, attributed to the attention mechanism at its core. Despite these successes, the attention mechanism of Transformers is associated with two well-known…

Machine Learning · Computer Science 2024-10-22 DongNyeong Heo , Heeyoul Choi

We study the approximation capabilities, convergence speeds and on-convergence behaviors of transformers trained on in-context recall tasks -- which requires to recognize the \emph{positional} association between a pair of tokens from…

Machine Learning · Computer Science 2025-10-22 Quan Nguyen , Thanh Nguyen-Tang

Transformers are the mainstream of NLP applications and are becoming increasingly popular in other domains such as Computer Vision. Despite the improvements in model quality, the enormous computation costs make Transformers difficult at…

Machine Learning · Computer Science 2021-10-22 Liu Liu , Zheng Qu , Zhaodong Chen , Yufei Ding , Yuan Xie

Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch? Recent works show that Transformers can be Turing-complete in terms of expressivity, but…

Machine Learning · Computer Science 2024-11-05 Emmanuel Abbe , Samy Bengio , Aryo Lotfi , Colin Sandon , Omid Saremi

Continual learning involves learning from a stream of data without repetition of data points, a scenario that is inherently complex due to distributional shift across tasks. We propose a query-only attention mechanism that discards keys and…

Machine Learning · Computer Science 2025-11-04 Gautham Bekal , Ashish Pujari , Scott David Kelly

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Machine Learning · Computer Science 2022-11-30 Bosheng Qin , Juncheng Li , Siliang Tang , Yueting Zhuang

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

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention),…

Machine Learning · Computer Science 2026-02-10 Mehryar Mohri

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can…

Computer Vision and Pattern Recognition · Computer Science 2021-04-23 Daniel Hernandez Diaz , Siyang Qin , Reeve Ingle , Yasuhisa Fujii , Alessandro Bissacco

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows…

Sound · Computer Science 2023-05-16 Qiquan Zhang , Hongxu Zhu , Qi Song , Xinyuan Qian , Zhaoheng Ni , Haizhou Li

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

Transformers, while powerful, suffer from quadratic computational complexity and the ever-growing Key-Value (KV) cache of the attention mechanism. This paper introduces Trellis, a novel Transformer architecture with bounded memory that…

Machine Learning · Computer Science 2026-01-01 Mahdi Karami , Ali Behrouz , Praneeth Kacham , Vahab Mirrokni

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Chen Zhu , Wei Ping , Chaowei Xiao , Mohammad Shoeybi , Tom Goldstein , Anima Anandkumar , Bryan Catanzaro

Position modeling plays a critical role in Transformers. In this paper, we focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We define attention resolution as an indicator of extrapolation. Then…

Computation and Language · Computer Science 2022-12-21 Yutao Sun , Li Dong , Barun Patra , Shuming Ma , Shaohan Huang , Alon Benhaim , Vishrav Chaudhary , Xia Song , Furu Wei