English
Related papers

Related papers: Delayed Attention Training Improves Length General…

200 papers

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu

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

Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitrarily long…

Machine Learning · Computer Science 2025-10-14 Ricardo Buitrago Ruiz , Albert Gu

It is a widely known issue that Transformers, when trained on shorter sequences, fail to generalize robustly to longer ones at test time. This raises the question of whether Transformer models are real reasoning engines, despite their…

Machine Learning · Computer Science 2025-04-04 Ruining Li , Gabrijel Boduljak , Jensen , Zhou

Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear models often suffer from limited recall performance, leading…

Computation and Language · Computer Science 2025-07-10 Dustin Wang , Rui-Jie Zhu , Steven Abreu , Yong Shan , Taylor Kergan , Yuqi Pan , Yuhong Chou , Zheng Li , Ge Zhang , Wenhao Huang , Jason Eshraghian

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

The paper studies the capabilities of Recurrent-Neural-Network sequence to sequence (RNN seq2seq) models in learning four transduction tasks: identity, reversal, total reduplication, and quadratic copying. These transductions are…

Computation and Language · Computer Science 2024-04-23 Zhengxiang Wang

The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI reasoning is whether models can extrapolate learned…

Machine Learning · Computer Science 2025-11-11 Yu Huang , Zixin Wen , Aarti Singh , Yuejie Chi , Yuxin Chen

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation…

Machine Learning · Computer Science 2019-07-15 Zhiwei Wang , Yao Ma , Zitao Liu , Jiliang Tang

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Computation and Language · Computer Science 2023-07-20 Jiayu Ding , Shuming Ma , Li Dong , Xingxing Zhang , Shaohan Huang , Wenhui Wang , Nanning Zheng , Furu Wei

Transformers struggle with length generalisation, displaying poor performance even on basic tasks. We test whether these limitations can be explained through two key failures of the self-attention mechanism. The first is the inability to…

Machine Learning · Computer Science 2025-10-07 Mattia Opper , Roland Fernandez , Paul Smolensky , Jianfeng Gao

Transformer has shown promising results in many sequence to sequence transformation tasks recently. It utilizes a number of feed-forward self-attention layers to replace the recurrent neural networks (RNN) in attention-based encoder decoder…

Computation and Language · Computer Science 2020-12-01 Pan Zhou , Ruchao Fan , Wei Chen , Jia Jia

Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying…

Computation and Language · Computer Science 2022-01-04 Dušan Variš , Ondřej Bojar

It has been observed in recent years that transformers have problems with length generalization for certain types of reasoning and arithmetic tasks. In particular, the performance of a transformer model trained on tasks (say addition) up to…

Machine Learning · Computer Science 2023-10-03 Pranjal Awasthi , Anupam Gupta

Recurrent neural networks (RNNs), such as linear attention and state-space models, have gained popularity due to their constant per-token complexity when processing long contexts. However, these recurrent models struggle with tasks that…

Computation and Language · Computer Science 2026-04-27 Xingyu Shen , Yingfa Chen , Zhen Leng Thai , Xu Han , Zhiyuan Liu , Maosong Sun

Retentive Network (RetNet) represents a significant advancement in neural network architecture, offering an efficient alternative to the Transformer. While Transformers rely on self-attention to model dependencies, they suffer from high…

Computation and Language · Computer Science 2025-06-10 Haiqi Yang , Zhiyuan Li , Yi Chang , Yuan Wu

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Computation and Language · Computer Science 2025-11-20 Xiuying Wei , Anunay Yadav , Razvan Pascanu , Caglar Gulcehre

Although transformer networks are recently employed in various vision tasks with outperforming performance, extensive training data and a lengthy training time are required to train a model to disregard an inductive bias. Using trainable…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Heegon Jin , Jongwon Choi

The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used maximum approximation, which simplifies, improves and speeds up…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-20 Albert Zeyer , André Merboldt , Ralf Schlüter , Hermann Ney

Transformer-based neural network architectures achieve state-of-the-art results in different domains, from natural language processing (NLP) to computer vision (CV). The key idea of Transformers, the attention mechanism, has already led to…

Machine Learning · Computer Science 2023-11-07 Alina Ermilova , Nikita Baramiia , Valerii Kornilov , Sergey Petrakov , Alexey Zaytsev
‹ Prev 1 2 3 10 Next ›