English
Related papers

Related papers: On the Optimization and Generalization of Multi-he…

200 papers

We study length generalization in sequence models on a composite problem involving both state tracking and associative recall. Prior work finds that recurrent networks handle state tracking well but struggle with recall, whereas…

Machine Learning · Computer Science 2025-10-02 Buu Phan , Reza Ebrahimi , Sanjay Haresh , Roland Memisevic

Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi-agent interactions, and multimodal context across perception, prediction, and planning. At the…

Machine Learning · Computer Science 2026-05-13 Juan Zhong , Yuhang Shi , Zukang Xu , Xi Chen

The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works have demonstrated that…

Computation and Language · Computer Science 2022-10-25 Javier Ferrando , Gerard I. Gállego , Marta R. Costa-jussà

Transformers and large language models (LLMs) have revolutionized machine learning, with attention mechanisms at the core of their success. As the landscape of attention variants expands, so too do the challenges of optimizing their…

Computation and Language · Computer Science 2025-02-24 Feiyang Chen , Yu Cheng , Lei Wang , Yuqing Xia , Ziming Miao , Lingxiao Ma , Fan Yang , Jilong Xue , Zhi Yang , Mao Yang , Haibo Chen

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple…

Computation and Language · Computer Science 2022-09-01 Zewei Sun , Shujian Huang , Xin-Yu Dai , Jiajun Chen

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

In this paper, we introduce the prior knowledge, multi-scale structure, into self-attention modules. We propose a Multi-Scale Transformer which uses multi-scale multi-head self-attention to capture features from different scales. Based on…

Computation and Language · Computer Science 2019-12-03 Qipeng Guo , Xipeng Qiu , Pengfei Liu , Xiangyang Xue , Zheng Zhang

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Computation and Language · Computer Science 2020-08-11 Sneha Mehta , Huzefa Rangwala , Naren Ramakrishnan

Deep neural networks often contain far more parameters than training examples, yet they still manage to generalize well in practice. Classical complexity measures such as VC-dimension or PAC-Bayes bounds usually become vacuous in this…

Machine Learning · Computer Science 2025-08-26 Aviral Dhingra

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Jiuk Hong , Chaehyeon Lee , Soyoun Bang , Heechul Jung

Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to the field of vision, achieving significant accomplishments…

Machine Learning · Computer Science 2024-11-25 Jiarui Jiang , Wei Huang , Miao Zhang , Taiji Suzuki , Liqiang Nie

Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this architecture is the Attention Mechanism, which solves the problem…

Machine Learning · Computer Science 2024-11-25 Bernhard Bermeitinger , Tomas Hrycej , Massimo Pavone , Julianus Kath , Siegfried Handschuh

Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remains limited. A recent work (Elhage et al., 2021) identified a ``rich'' in-context mechanism…

Machine Learning · Computer Science 2025-01-30 Mingze Wang , Ruoxi Yu , Weinan E , Lei Wu

Transformers have recently revolutionized many domains in modern machine learning and one salient discovery is their remarkable in-context learning capability, where models can solve an unseen task by utilizing task-specific prompts without…

Machine Learning · Computer Science 2023-10-10 Yu Huang , Yuan Cheng , Yingbin Liang

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs. In essence, what self-attention does is to infer the pairwise relations between the elements of the inputs, and modify the…

Machine Learning · Computer Science 2021-03-09 Lemeng Wu , Xingchao Liu , Qiang Liu

Simultaneous machine translation models start generating a target sequence before they have encoded or read the source sequence. Recent approaches for this task either apply a fixed policy on a state-of-the art Transformer model, or a…

Computation and Language · Computer Science 2019-09-30 Xutai Ma , Juan Pino , James Cross , Liezl Puzon , Jiatao Gu

Transformer has become the dominant architecture for sequence modeling, yet a detailed understanding of how its structural parameters influence expressive power remains limited. In this work, we study the approximation properties of…

Machine Learning · Computer Science 2026-04-01 Penghao Yu , Haotian Jiang , Zeyu Bao , Ruoxi Yu , Qianxiao Li

Attention mechanism has gained huge popularity due to its effectiveness in achieving high accuracy in different domains. But attention is opportunistic and is not justified by the content or usability of the content. Transformer like…

Computer Vision and Pattern Recognition · Computer Science 2020-06-26 Chiranjib Sur