English
Related papers

Related papers: RiemannFormer: A Framework for Attention in Curved…

200 papers

The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour. Some studies have…

Computation and Language · Computer Science 2020-08-14 Madhura Pande , Aakriti Budhraja , Preksha Nema , Pratyush Kumar , Mitesh M. Khapra

Linear transformers aim to reduce the quadratic space-time complexity of vanilla transformers. However, they usually suffer from degraded performances on various tasks and corpus. In this paper, we examine existing kernel-based linear…

Computation and Language · Computer Science 2022-10-20 Zhen Qin , XiaoDong Han , Weixuan Sun , Dongxu Li , Lingpeng Kong , Nick Barnes , Yiran Zhong

Reconstructing physical field tensors from \textit{in situ} observations, such as radio maps and ocean sound speed fields, is crucial for enabling environment-aware decision making in various applications, e.g., wireless communications and…

Signal Processing · Electrical Eng. & Systems 2025-06-16 Panqi Chen , Siyuan Li , Lei Cheng , Xiao Fu , Yik-Chung Wu , Sergios Theodoridis

Existing attention mechanisms are trained to attend to individual items in a collection (the memory) with a predefined, fixed granularity, e.g., a word token or an image grid. We propose area attention: a way to attend to areas in the…

Machine Learning · Computer Science 2020-05-11 Yang Li , Lukasz Kaiser , Samy Bengio , Si Si

Transformers have revolutionized natural language processing, but their quadratic complexity with respect to sequence length remains a fundamental bottleneck for long-range modeling. While sparse attention mechanisms like RingAttention…

Computation and Language · Computer Science 2026-03-31 Dong Liu , Yanxuan Yu

The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms. Simply put, the attention mechanisms learn to attend to specific parts of the input dispensing recurrence…

Computation and Language · Computer Science 2020-12-24 Dongsheng Wang , Casper Hansen , Lucas Chaves Lima , Christian Hansen , Maria Maistro , Jakob Grue Simonsen , Christina Lioma

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Computation and Language · Computer Science 2021-03-23 Hao Peng , Nikolaos Pappas , Dani Yogatama , Roy Schwartz , Noah A. Smith , Lingpeng Kong

Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories. Existing deep network approaches are mainly based on class activation map, which focuses on…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Hui Su , Yue Ye , Zhiwei Chen , Mingli Song , Lechao Cheng

This paper advances a novel architectural schema anchored upon the Transformer paradigm and innovatively amalgamates the K-means categorization algorithm to augment the contextual apprehension capabilities of the schema. The transformer…

Computation and Language · Computer Science 2025-01-22 Yuwei Zhang , Junming Huang , Sitong Liu , Zexi Chen , Zizheng Li

Relying entirely on an attention mechanism, the Transformer introduced by Vaswani et al. (2017) achieves state-of-the-art results for machine translation. In contrast to recurrent and convolutional neural networks, it does not explicitly…

Computation and Language · Computer Science 2018-04-16 Peter Shaw , Jakob Uszkoreit , Ashish Vaswani

Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This bias is closely connected to the Lost-in-the-Middle phenomenon, where models underutilize…

Machine Learning · Computer Science 2026-05-28 Hanna Herasimchyk , Robin Labryga , Tomislav Prusina , Sören Laue

An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective…

Computation and Language · Computer Science 2021-05-20 Kaiser Sun , Ana Marasović

Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. In this work, we demonstrate a set of methods for…

Computation and Language · Computer Science 2021-03-30 Jesse Vig , Ali Madani , Lav R. Varshney , Caiming Xiong , Richard Socher , Nazneen Fatema Rajani

Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

Machine Learning · Computer Science 2025-08-19 Parsa Omidi , Xingshuai Huang , Axel Laborieux , Bahareh Nikpour , Tianyu Shi , Armaghan Eshaghi

Neural networks using transformer-based architectures have recently demonstrated great power and flexibility in modeling sequences of many types. One of the core components of transformer networks is the attention layer, which allows…

Machine Learning · Computer Science 2019-07-16 Matthew Spellings

We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention…

Machine Learning · Computer Science 2022-06-28 Weizhe Hua , Zihang Dai , Hanxiao Liu , Quoc V. Le

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen