When Can World Models Recover Physical Laws?
stat.OT, cs.AI, cs.IT, cs.LG, cs.SY, eess.SY, math.IT
Submitted: 2026-09-15
Updated: 2026-09-15
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- World Models
- A Sparse Bayesian Approach to the Identification of Nonlinear State-Space Systems
- Towards Causal Representation Learning
- Lower Bounds for Nonparametric Estimation of Ordinary Differential Equations
- A Sampling Theorem for Exact Identification of Continuous-time Nonlinear Dynamical Systems