English

Temporal Lifting as Latent-Space Regularization for Continuous-Time Flow Models in AI Systems

Machine Learning 2026-01-28 v2 Artificial Intelligence

Abstract

We present a latent-space formulation of adaptive temporal lifting for continuous-time dynamical systems. The method introduces a smooth monotone mapping tτ(t)t \mapsto \tau(t) that regularizes near-singular behavior of the underlying flow while preserving its conservation laws. In the lifted coordinate, trajectories such as those of the incompressible Navier-Stokes equations on the torus T3\mathbb{T}^3 become globally smooth. From the standpoint of machine-learning dynamics, temporal lifting acts as a continuous-time normalization operator that can stabilize physics-informed neural networks and other latent-flow architectures used in AI systems. The framework links analytic regularity theory with representation-learning methods for stiff or turbulent processes.

Keywords

Cite

@article{arxiv.2510.09805,
  title  = {Temporal Lifting as Latent-Space Regularization for Continuous-Time Flow Models in AI Systems},
  author = {Jeffrey Camlin},
  journal= {arXiv preprint arXiv:2510.09805},
  year   = {2026}
}

Comments

7 pages, 1 figure, 1 table, 1 algorithm

R2 v1 2026-07-01T06:30:22.875Z