When do World Models Successfully Learn Dynamical Systems?

• URL: http://arxiv.org/abs/2507.04898v1
• Date: Mon, 07 Jul 2025 11:29:18 GMT
• Title: When do World Models Successfully Learn Dynamical Systems?
• Authors: Edmund Ross, Claudia Drygala, Leonhard Schwarz, Samir Kaiser, Francesca di Mare, Tobias Breiten, Hanno Gottschalk,
• Abstract summary: We propose a theoretical framework that explains why projecting time slices into a low-dimensional space and then concatenating to form a history ('Tokenization') is so effective at learning physics datasets.<n>We develop a sequence of models with increasing complexity, starting with least-squares regression and progressing through simple linear layers, shallow adversarial learners, and ultimately full-scale generative adversarial networks (GANs)<n>We evaluate these models on a variety of datasets, including modified forms of the heat and wave equations, the chaotic regime 2D Kuramoto-Sivashinsky equation, and a challenging computational fluid dynamics (
• Score: 1.0470286407954037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we explore the use of compact latent representations with learned time dynamics ('World Models') to simulate physical systems. Drawing on concepts from control theory, we propose a theoretical framework that explains why projecting time slices into a low-dimensional space and then concatenating to form a history ('Tokenization') is so effective at learning physics datasets, and characterise when exactly the underlying dynamics admit a reconstruction mapping from the history of previous tokenized frames to the next. To validate these claims, we develop a sequence of models with increasing complexity, starting with least-squares regression and progressing through simple linear layers, shallow adversarial learners, and ultimately full-scale generative adversarial networks (GANs). We evaluate these models on a variety of datasets, including modified forms of the heat and wave equations, the chaotic regime 2D Kuramoto-Sivashinsky equation, and a challenging computational fluid dynamics (CFD) dataset of a 2D K\'arm\'an vortex street around a fixed cylinder, where our model is successfully able to recreate the flow.

Related papers

• Generalized Factor Neural Network Model for High-dimensional Regression [50.554377879576066]
  We tackle the challenges of modeling high-dimensional data sets with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships.<n>Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression.
  arXiv  Detail & Related papers  (2025-02-16T23:13:55Z)
• Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flows [4.798951413107239]
  We propose a novel framework, Graph-based Learning of Effective Dynamics (Graph-LED), that leverages graph neural networks (GNNs) and an attention-based autoregressive model.<n>We evaluate the proposed approach on a suite of fluid dynamics problems, including flow past a cylinder and flow over a backward-facing step over a range of Reynolds numbers.
  arXiv  Detail & Related papers  (2025-02-11T22:14:30Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models [9.318262213262866]
  We introduce a novel framework for learning semi-structured dynamics models for contact-rich systems. We make accurate long-horizon predictions with substantially less data than prior methods. We validate our approach on a real-world Unitree Go1 quadruped robot.
  arXiv  Detail & Related papers  (2024-10-11T18:11:21Z)
• Zero-shot Imputation with Foundation Inference Models for Dynamical Systems [5.549794481031468]
  We offer a fresh perspective on the classical problem of imputing missing time series data, whose underlying dynamics are assumed to be determined by ODEs.<n>We propose a novel supervised learning framework for zero-shot time series imputation, through parametric functions satisfying some (hidden) ODEs.<n>We empirically demonstrate that one and the same (pretrained) recognition model can perform zero-shot imputation across 63 distinct time series with missing values.
  arXiv  Detail & Related papers  (2024-02-12T11:48:54Z)
• Generative learning for nonlinear dynamics [7.6146285961466]
  generative machine learning models create realistic outputs far beyond their training data. These successes suggest that generative models learn to effectively parametrize and sample arbitrarily complex distributions. We aim to connect these classical works to emerging themes in large-scale generative statistical learning.
  arXiv  Detail & Related papers  (2023-11-07T16:53:56Z)
• Knowledge-based Deep Learning for Modeling Chaotic Systems [7.075125892721573]
  This paper considers extreme events and their dynamics and proposes models based on deep neural networks, called knowledge-based deep learning (KDL) Our proposed KDL can learn the complex patterns governing chaotic systems by jointly training on real and simulated data. We validate our model by assessing it on three real-world benchmark datasets: El Nino sea surface temperature, San Juan Dengue viral infection, and Bjornoya daily precipitation.
  arXiv  Detail & Related papers  (2022-09-09T11:46:25Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning [9.36739413306697]
  Learning dynamical models from data plays a vital role in engineering design, optimization, and predictions. We use deep learning to identify low-dimensional embeddings for high-fidelity dynamical systems.
  arXiv  Detail & Related papers  (2021-11-25T10:09:00Z)
• Constructing Neural Network-Based Models for Simulating Dynamical Systems [59.0861954179401]
  Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. This paper provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
  arXiv  Detail & Related papers  (2021-11-02T10:51:42Z)
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning [87.38675639186405]
  We propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs.
  arXiv  Detail & Related papers  (2021-05-17T15:33:25Z)
• Learning Stable Deep Dynamics Models [91.90131512825504]
  We propose an approach for learning dynamical systems that are guaranteed to be stable over the entire state space. We show that such learning systems are able to model simple dynamical systems and can be combined with additional deep generative models to learn complex dynamics.
  arXiv  Detail & Related papers  (2020-01-17T00:04:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.