Cover Image

From independent patches to coordinated attention: Controlling information flow in vision transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Murphy, Kieran A.
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Latent attention on masked patches for flow reconstruction
by: Eze, Ben, et al.
Published: (2026)

Comparing the information content of probabilistic representation spaces
by: Murphy, Kieran A., et al.
Published: (2024)

Integrating attention into explanation frameworks for language and vision transformers
by: Eggen, Marte, et al.
Published: (2025)

InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control
by: Murphy, Kieran A.
Published: (2026)

Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck
by: Murphy, Kieran A., et al.
Published: (2023)

Which bits went where? Past and future transfer entropy decomposition with the information bottleneck
by: Murphy, Kieran A., et al.
Published: (2024)

Easy attention: A simple attention mechanism for temporal predictions with transformers
by: Sanchis-Agudo, Marcial, et al.
Published: (2023)

Pi-transformer: A prior-informed dual-attention model for multivariate time-series anomaly detection
by: Maleki, Sepehr, et al.
Published: (2025)

Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
by: Calleo, Yuri
Published: (2025)

Integrated electro-optic attention nonlinearities for transformers
by: Mickeler, Luis, et al.
Published: (2026)

Sensorformer: Cross-patch attention with global-patch compression is effective for high-dimensional multivariate time series forecasting
by: Qin, Liyang, et al.
Published: (2025)

Information decomposition in complex systems via machine learning
by: Murphy, Kieran A., et al.
Published: (2023)

Controlling changes to attention logits
by: Anson, Ben, et al.
Published: (2025)

Enhancing compact convolutional transformers with super attention
by: Leandre, Simpenzwe Honore, et al.
Published: (2025)

Surveying the space of descriptions of a composite system with machine learning
by: Murphy, Kieran A., et al.
Published: (2024)

Static and multivariate-temporal attentive fusion transformer for readmission risk prediction
by: Sun, Zhe, et al.
Published: (2024)

Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
by: Kim, Changhun, et al.
Published: (2025)

Visualizing the loss landscapes of physics-informed neural networks
by: Rowan, Conor, et al.
Published: (2026)

A standard transformer and attention with linear biases for molecular conformer generation
by: Gurev, Viatcheslav, et al.
Published: (2025)

Sparse patches adversarial attacks via extrapolating point-wise information
by: Nemcovsky, Yaniv, et al.
Published: (2024)

Critical attention scaling in long-context transformers
by: Chen, Shi, et al.
Published: (2025)

Linear attention is (maybe) all you need (to understand transformer optimization)
by: Ahn, Kwangjun, et al.
Published: (2023)

Learning spatially structured open quantum dynamics with regional-attention transformers
by: Du, Dounan, et al.
Published: (2025)

How to use and interpret activation patching
by: Heimersheim, Stefan, et al.
Published: (2024)

Linear cost mutual information estimation and independence test of similar performance as HSIC
by: Duda, Jarek, et al.
Published: (2025)

Physics-informed Discretization-independent Deep Compositional Operator Network
by: Zhong, Weiheng, et al.
Published: (2024)

Scalable iterative pruning of large language and vision models using block coordinate descent
by: Rosenberg, Gili, et al.
Published: (2024)

Self-attention-based non-linear basis transformations for compact latent space modelling of dynamic optical fibre transmission matrices
by: Zheng, Yijie, et al.
Published: (2024)

An Adaptive Volatility-based Learning Rate Scheduler
by: Ren, Kieran Chai Kai
Published: (2025)

A hybrid transformer and attention based recurrent neural network for robust and interpretable sentiment analysis of tweets
by: Jahin, Md Abrar, et al.
Published: (2024)

A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand prediction
by: Qu, Haohao, et al.
Published: (2023)

Convergence theory for Hermite approximations under adaptive coordinate transformations
by: Saleh, Yahya
Published: (2026)

DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised $h$-transform
by: Denker, Alexander, et al.
Published: (2024)

In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
by: Smart, Matthew, et al.
Published: (2025)

Reorganizing attention-space geometry with expressive attention
by: Gros, Claudius
Published: (2024)

Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder
by: Akhtar, Sheikh Waqas
Published: (2024)

Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi
by: Koresh, Ella, et al.
Published: (2025)

Physics-informed neural particle flow for the Bayesian update step
by: Csuzdi, Domonkos, et al.
Published: (2026)

Speech transformer models for extracting information from baby cries
by: Bonafos, Guillem, et al.
Published: (2025)

Clustering in pure-attention hardmax transformers and its role in sentiment analysis
by: Alcalde, Albert, et al.
Published: (2024)