English
Related papers

Related papers: How transformers learn structured data: insights f…

200 papers

Because language is creative, any reasonable language model must generalize, deciding what to say in novel contexts by using information from similar contexts. But what about contexts that are not novel but merely infrequent? In…

Computation and Language · Computer Science 2026-02-05 Vsevolod Kapatsinski

In transformers, the positional encoding (PE) provides essential information that distinguishes the position and order amongst tokens in a sequence. Most prior investigations of PE effects on generalization were tailored to 1D input…

Machine Learning · Computer Science 2025-06-24 Takuya Ito , Luca Cocchi , Tim Klinger , Parikshit Ram , Murray Campbell , Luke Hearne

Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of…

Disordered Systems and Neural Networks · Physics 2022-10-17 Alessandro Ingrosso , Sebastian Goldt

Transformers have exhibited exceptional capabilities in sequence modeling tasks, leveraging self-attention and in-context learning. Critical to this success are induction heads, attention circuits that enable copying tokens based on their…

Machine Learning · Computer Science 2025-09-11 Francesco D'Angelo , Francesco Croce , Nicolas Flammarion

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time. In contrast to static models which use the same computation graph for all instances, adaptive networks can dynamically adjust…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Hao Li , Hong Zhang , Xiaojuan Qi , Ruigang Yang , Gao Huang

Transformer-based models are at the forefront in long time-series forecasting (LTSF). While in many cases, these models are able to achieve state of the art results, they suffer from a bias toward low-frequencies in the data and high…

Machine Learning · Computer Science 2026-05-13 Elisha Dayag , Nhat Thanh Van Tran , Jack Xin

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional…

Machine Learning · Computer Science 2024-07-04 Francesco Cagnetta , Leonardo Petrini , Umberto M. Tomasini , Alessandro Favero , Matthieu Wyart

The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-21 Jack Valmadre , Luca Bertinetto , João F. Henriques , Andrea Vedaldi , Philip H. S. Torr

Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks. However, it is evident that state-of-the-art (SOTA) sequence-based models like the Transformer…

Machine Learning · Computer Science 2020-02-20 Xuan-Phi Nguyen , Shafiq Joty , Steven C. H. Hoi , Richard Socher

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

Transformer networks are the de facto standard architecture in natural language processing. To date, there are no theoretical analyses of the Transformer's ability to capture tree structures. We focus on the ability of Transformer networks…

Computation and Language · Computer Science 2021-12-23 Qi He , João Sedoc , Jordan Rodu

While conventional Transformers generally operate on sequence data, they can be used in conjunction with structure models, typically SE(3)-invariant or equivariant graph neural networks (GNNs), for 3D applications such as protein structure…

Machine Learning · Computer Science 2025-08-04 Isaac Ellmen , Constantin Schneider , Matthew I. J. Raybould , Charlotte M. Deane

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Model transformations operate on models conforming to precisely defined metamodels. Consequently, it often seems relatively easy to chain them: the output of a transformation may be given as input to a second one if metamodels match.…

Artificial Intelligence · Computer Science 2010-03-04 Raphael Chenouard , Frédéric Jouault

Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks. Various neural network models are proposed to learn from tree-structured program representations, e.g.,…

Software Engineering · Computer Science 2023-01-10 Wenhan Wang , Kechi Zhang , Ge Li , Shangqing Liu , Anran Li , Zhi Jin , Yang Liu

The growth of global consumption has motivated important applications of deep learning to smart manufacturing and machine health monitoring. In particular, analyzing vibration data offers great potential to extract meaningful insights into…

Machine Learning · Computer Science 2024-05-30 Anthony Zhou , Amir Barati Farimani

Transformers have achieved great success across a wide range of applications, yet the theoretical foundations underlying their success remain largely unexplored. To demystify the strong capacities of transformers applied to versatile…

Machine Learning · Computer Science 2026-03-25 Chenyang Zhang , Qingyue Zhao , Quanquan Gu , Yuan Cao

Neural sequence models based on the transformer architecture have demonstrated remarkable \emph{in-context learning} (ICL) abilities, where they can perform new tasks when prompted with training and test examples, without any parameter…

Machine Learning · Computer Science 2023-07-07 Yu Bai , Fan Chen , Huan Wang , Caiming Xiong , Song Mei

Designing learning systems which are invariant to certain data transformations is critical in machine learning. Practitioners can typically enforce a desired invariance on the trained model through the choice of a network architecture, e.g.…

Machine Learning · Computer Science 2022-10-26 Cédric Rommel , Thomas Moreau , Alexandre Gramfort

In this paper, we propose to exploit the rich hierarchical features of deep convolutional neural networks to improve the accuracy and robustness of visual tracking. Deep neural networks trained on object recognition datasets consist of…

Computer Vision and Pattern Recognition · Computer Science 2018-08-14 Chao Ma , Jia-Bin Huang , Xiaokang Yang , Ming-Hsuan Yang