English
Related papers

Related papers: Dynamic metastability in the self-attention model

200 papers

Metastability, i.e., partial relaxation to long-lived, quasi-stationary states before true asymptotic equilibrium sets in, emerges ubiquitously in classical and quantum dynamical systems as a result of timescales separation. In open quantum…

Mesoscale and Nanoscale Physics · Physics 2026-02-17 Vincent P. Flynn , Lorenza Viola , Benedetta Flebus

We study a catching-up algorithm for a class of differential inclusions driven by maximal monotone operators with continuous perturbations. Using a decomposition of the monotone operator into the closed convex hull of its single-valued part…

Optimization and Control · Mathematics 2026-04-14 Tan H. Cao , Hassan Saoud

Self-organization is ubiquitous in nature and mind. However, machine learning and theories of cognition still barely touch the subject. The hurdle is that general patterns are difficult to define in terms of dynamical equations and…

Artificial Intelligence · Computer Science 2023-02-07 Danilo Vasconcellos Vargas , Tham Yik Foong , Heng Zhang

Actively propelled particles undergoing dissipative collisions are known to develop a state of spatially distributed coherently moving clusters. For densities larger than a characteristic value clusters grow in time and form a stationary…

Soft Condensed Matter · Physics 2013-04-23 Christoph A. Weber , Florian Thüroff , Erwin Frey

We study self-attention dynamics on the unit sphere as an interacting particle system arising from an idealized Transformer-type update. Under a symmetry assumption on weight matrices given by $Q^\top K=V=V^\top$, the flow admits a…

Dynamical Systems · Mathematics 2026-04-30 Christian Kuehn , Jaeyoung Yoon

We develop a finite-dimensional sensitivity framework for studying stability in learning systems whose states include representations, parameters, and update variables. The central object is the \emph{Learning Stability Profile}, a…

Machine Learning · Computer Science 2026-05-26 Ronald Katende

The transformer architecture and variants presented remarkable success across many machine learning tasks in recent years. This success is intrinsically related to the capability of handling long sequences and the presence of…

Machine Learning · Computer Science 2022-06-15 Luckeciano C. Melo

In this note we discuss metastability in a long-but-finite range disordered model for the glass transition. We show that relaxation is dominated by configuration belonging to metastable states and associate an in principle computable…

Statistical Mechanics · Physics 2009-11-11 Silvio Franz

We study the energy flow of dissipative dynamics on infinite lattices, allowing the total energy to be infinite and considering formally gradient dynamics. We show that in spatial dimensions 1,2, the flow is for almost all times arbitrarily…

Dynamical Systems · Mathematics 2013-01-16 Sinisa Slijepcevic

We show how the tracer motion of tagged, distinguishable particles can effectively describe transport in various homogeneous quantum many-body systems with constraints. We consider systems of spinful particles on a one-dimensional lattice…

Strongly Correlated Electrons · Physics 2022-10-20 Johannes Feldmeier , William Witczak-Krempa , Michael Knap

Using agent-based simulations of self-propelled particles subject to short-range repulsion and nematic alignment we explore the dynamical phases of a dense active material confined to the surface of a sphere. We map the dynamical phase…

Soft Condensed Matter · Physics 2018-04-25 Silke Henkes , M. Cristina Marchetti , Rastko Sknepnek

Self-attention is an attention mechanism that learns a representation by relating different positions in the sequence. The transformer, which is a sequence model solely based on self-attention, and its variants achieved state-of-the-art…

Sound · Computer Science 2019-06-13 Minz Won , Sanghyuk Chun , Xavier Serra

We present a derivation of a recently proposed theory for the time dependence of density fluctuations in stationary states of strongly interacting, athermal, self-propelled particles. The derivation consists of two steps. First, we start…

Soft Condensed Matter · Physics 2016-01-13 Grzegorz Szamel

In-Context Learning (ICL) in transformers acts as an online associative memory and is believed to underpin their high performance on complex sequence processing tasks. However, in gated linear attention models, this memory has a fixed…

Machine Learning · Computer Science 2026-02-12 Djohan Bonnet , Jamie Lohoff , Jan Finkbeiner , Elidona Skhikerujah , Emre Neftci

A study of the gas dynamics of a dilute collection of the inelastically colliding hard spheres is presented. When diffusive processes are neglected the gas density blows up in a finite time. The blowup is the mathematical expression for one…

Soft Condensed Matter · Physics 2008-12-09 Itzhak Fouxon

Self-attention has greatly contributed to the success of the widely used Transformer architecture by enabling learning from data with long-range dependencies. In an effort to improve performance, a gated attention model that leverages a…

Machine Learning · Computer Science 2026-02-03 Viet Nguyen , Tuan Minh Pham , Thinh Cao , Tan Dinh , Huy Nguyen , Nhat Ho , Alessandro Rinaldo

A mode-coupling theory for the slow single-particle dynamics in fluids adsorbed in disordered porous media is derived, which complements previous work on the collective dynamics [V. Krakoviack, Phys. Rev. E 75, 031503 (2007)]. Its…

Disordered Systems and Neural Networks · Physics 2009-06-10 V. Krakoviack

Rich out of equilibrium collective dynamics of strongly interacting large assemblies emerge in many areas of science. Some intriguing and not fully understood examples are the glassy arrest in atomic, molecular or colloidal systems,…

Statistical Mechanics · Physics 2023-05-03 Leticia F. Cugliandolo

My goal is to study the dynamics of the Universe from a relational perspective based on the happening of events in temporal relation to each other and their respective points of reference. Accordingly, the flow of time was modeled as the…

General Physics · Physics 2025-05-13 Bruce M Boman

The Transformer, a breakthrough architecture in artificial intelligence, owes its success to the attention mechanism, which utilizes long-range interactions in sequential data, enabling the emergent coherence between large language models…

Artificial Intelligence · Computer Science 2026-04-23 Zihan Zhou , Bo-Wei Qin , Kai Du , Wei Lin