English
Related papers

Related papers: The Diffusion-Attention Connection

200 papers

This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge lies in mitigating the duplicate and common-place strokes, which often lead to less…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Lingyu Liu , Yaxiong Wang , Li Zhu , Lizi Liao , Zhedong Zheng

We introduce Hodge Diffusion Maps, a novel manifold learning algorithm designed to analyze and extract topological information from high-dimensional data-sets. This method approximates the exterior derivative acting on differential forms,…

Machine Learning · Computer Science 2025-04-11 Alvaro Almeida Gomez , Jorge Duque Franco

Transformers have achieved remarkable progress in time series forecasting, yet their reliance on deterministic dot-product attention limits their capacity to model uncertainty and nonlinear dependencies across multivariate temporal…

Machine Learning · Computer Science 2026-03-24 Bulent Haznedar , Levent Karacan

Transformer-based models have demonstrated exceptional performance across diverse domains, becoming the state-of-the-art solution for addressing sequential machine learning problems. Even though we have a general understanding of the…

Disordered Systems and Neural Networks · Physics 2024-06-12 Ángel Poc-López , Miguel Aguilera

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras

We show that particle transport in a uniform, quantum multi-baker map, is generically ballistic in the long time limit, for any fixed value of Planck's constant. However, for fixed times, the semi-classical limit leads to diffusion. Random…

Quantum Physics · Physics 2009-11-07 Daniel K. Wojcik , J. R. Dorfman

The diffusion of a system of ferromagnetic dipoles confined in a quasi-one-dimensional parabolic trap is studied using Brownian dynamics simulations. We show that the dynamics of the system is tunable by an in-plane external homogeneous…

Soft Condensed Matter · Physics 2013-01-15 D. Lucena , W. P. Ferreira , F. F. Munarin , G. A. Farias , F. M. Peeters

A new diffuse interface model for a two-phase flow of two incompressible fluids with different densities is introduced using methods from rational continuum mechanics. The model fulfills local and global dissipation inequalities and is…

Fluid Dynamics · Physics 2011-04-08 H. Abels , H. Garcke , G. Grün

Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Zhengcong Fei , Mingyuan Fan , Changqian Yu , Debang Li , Junshi Huang

We study Diffusion Schr\"odinger Bridge (DSB) models in the context of dynamical astrophysical systems, specifically tackling observational inverse prediction tasks within Giant Molecular Clouds (GMCs) for star formation. We introduce the…

Instrumentation and Methods for Astrophysics · Physics 2025-11-13 Ye Zhu , Duo Xu , Zhiwei Deng , Jonathan C. Tan , Olga Russakovsky

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

Light-Front quantization is one of the most promising and physical tools towards studying deep inelastic scattering on the basis of quark gluon degrees of freedom. The simplified vacuum structure (nontrivial vacuum effects can only appear…

High Energy Physics - Phenomenology · Physics 2007-05-23 M. Burkardt

We introduce diffusion geometry as a new framework for geometric and topological data analysis. Diffusion geometry uses the Bakry-Emery $\Gamma$-calculus of Markov diffusion operators to define objects from Riemannian geometry on a wide…

Metric Geometry · Mathematics 2024-07-03 Iolo Jones

The diverse quantization phenomena in 2D condensed-matter systems, being due to a uniform perpendicular magnetic field and the geometry-created lattice symmetries, are the focuses of this book. They cover the diversified magneto-electronic…

Computational Physics · Physics 2019-05-09 Chiun-Yan Lin , Thi-Nga Do , Jhao-Ying Wu , Po-Hsin Shih , Shih-Yang Lin , Ching-Hong Ho , Ming-Fa Lin

Despite the remarkable empirical performance of Transformers, their theoretical understanding remains elusive. Here, we consider a deep multi-head self-attention network, that is closely related to Transformers yet analytically tractable.…

Machine Learning · Computer Science 2024-12-10 Lorenzo Tiberi , Francesca Mignacco , Kazuki Irie , Haim Sompolinsky

The structure of the diffusion regions in antiparallel magnetic reconnection is investigated by means of a theory and a Vlasov simulation. The magnetic diffusion is considered as relaxation to the frozen-in state, which depends on a…

Solar and Stellar Astrophysics · Physics 2014-03-31 Seiji Zenitani , Takayuki Umeda

Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint. However, the design of hand-crafted windows, which is data-agnostic,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Qiming Zhang , Jing Zhang , Yufei Xu , Dacheng Tao

Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a mixed-graph-based optimization algorithm to forecast traffic with…

Machine Learning · Computer Science 2026-02-04 Ji Qi , Tam Thuc Do , Mingxiao Liu , Zhuoshi Pan , Yuzhe Li , Gene Cheung , H. Vicky Zhao

Viewing Transformers as interacting particle systems, we describe the geometry of learned representations when the weights are not time dependent. We show that particles, representing tokens, tend to cluster toward particular limiting…

Machine Learning · Computer Science 2024-02-14 Borjan Geshkovski , Cyril Letrouit , Yury Polyanskiy , Philippe Rigollet

Neural networks transform data through learned representations whose geometry affects separation, contraction, and generalization. Recent work studies this geometry using discrete curvature on neighborhood graphs, suggesting Ricci-flow-like…

Machine Learning · Computer Science 2026-05-05 Kanishka Reddy
‹ Prev 1 8 9 10 Next ›