English
Related papers

Related papers: Logic and the $2$-Simplicial Transformer

200 papers

Transformer-based models have demonstrated remarkable in-context learning capabilities, prompting extensive research into its underlying mechanisms. Recent studies have suggested that Transformers can implement first-order optimization…

Machine Learning · Computer Science 2024-03-06 Angeliki Giannou , Liu Yang , Tianhao Wang , Dimitris Papailiopoulos , Jason D. Lee

To enhance the computational efficiency of quantized Transformers, we replace the dot-product and Softmax-based attention with an alternative mechanism involving addition and ReLU activation only. This side-steps the expansion to double…

Machine Learning · Computer Science 2025-10-02 Rickard Brännvall , Andrei Stoian

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

Attention, specifically scaled dot-product attention, has proven effective for natural language, but it does not have a mechanism for handling hierarchical patterns of arbitrary nesting depth, which limits its ability to recognize certain…

Computation and Language · Computer Science 2024-01-25 Brian DuSell , David Chiang

In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The efficient design makes the incorporation between attention…

Computer Vision and Pattern Recognition · Computer Science 2020-08-21 Rui Li , Jianlin Su , Chenxi Duan , Shunyi Zheng

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Computation and Language · Computer Science 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Transformers have shown superior performance on various vision tasks. Their large receptive field endows Transformer models with higher representation power than their CNN counterparts. Nevertheless, simply enlarging the receptive field…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Zhuofan Xia , Xuran Pan , Shiji Song , Li Erran Li , Gao Huang

Attention-based beamformers have recently been shown to be effective for multi-channel speech recognition. However, they are less capable at capturing local information. In this work, we propose a 2D Conv-Attention module which combines…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-18 Bhargav Pulugundla , Yang Gao , Brian King , Gokce Keskin , Harish Mallidi , Minhua Wu , Jasha Droppo , Roland Maas

Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Hila Chefer , Shir Gur , Lior Wolf

The computational complexity of the self-attention mechanism in Transformer models significantly limits their ability to generalize over long temporal durations. Memory-augmentation, or the explicit storing of past information in external…

Computation and Language · Computer Science 2022-11-29 Omri Raccah , Phoebe Chen , Ted L. Willke , David Poeppel , Vy A. Vo

A method named simple2complex for modeling and training deep neural networks is proposed. Simple2complex train deep neural networks by smoothly adding more and more layers to the shallow networks, as the learning procedure going on, the…

Machine Learning · Computer Science 2016-05-03 Ming Li

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can detect and focus on relevant sources of information for the given learning objective.…

Machine Learning · Computer Science 2020-05-26 Dat Thanh Tran , Nikolaos Passalis , Anastasios Tefas , Moncef Gabbouj , Alexandros Iosifidis

Operator learning for Partial Differential Equations (PDEs) is rapidly emerging as a promising approach for surrogate modeling of intricate systems. Transformers with the self-attention mechanism$\unicode{x2013}$a powerful tool originally…

Machine Learning · Computer Science 2024-05-17 Junfeng Chen , Kailiang Wu

In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to…

Computer Vision and Pattern Recognition · Computer Science 2017-09-15 Yan Wang , Lingxi Xie , Chenxi Liu , Ya Zhang , Wenjun Zhang , Alan Yuille

Transformers have reshaped machine learning by utilizing attention mechanisms to capture complex patterns in large datasets, leading to significant improvements in performance. This success has contributed to the belief that "bigger means…

Machine Learning · Computer Science 2025-05-28 Hemanth Saratchandran , Damien Teney , Simon Lucey

Transformers generalize to novel compositions of structures and entities after being trained on a complex dataset, but easily overfit on datasets of insufficient complexity. We observe that when the training set is sufficiently complex, the…

Computation and Language · Computer Science 2024-02-12 Yichen Jiang , Xiang Zhou , Mohit Bansal

Inductive learning aims to construct general models from specific examples, guided by biases that influence hypothesis selection and determine generalization capacity. In this work, we focus on characterizing the relational inductive biases…

Transformers increasingly dominate the machine learning landscape across many tasks and domains, which increases the importance for understanding their outputs. While their attention modules provide partial insight into their inner…

Computer Vision and Pattern Recognition · Computer Science 2023-01-23 Moritz Böhle , Mario Fritz , Bernt Schiele

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both…

Machine Learning · Computer Science 2023-11-17 Clayton Sanford , Daniel Hsu , Matus Telgarsky