cs.LGSep 30, 2025

Benchmarking Stochastic Interpolants for Modeling Physical Systems

Authors: Anthony Zhou, Alexander Wikner, Amaury Lancelin, Pedram Hassanzadeh, Amir Barati Farimani

Organizations: Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Department of Geophysical Sciences, Committee on Computational and Applied Mathematics, University of Chicago, Chicago, IL 60637, USA · LMD/IPSL, CNRS, ENS, Université PSL, École Polytechnique, Institut Polytechnique de Paris, Sorbonne Université, Réseau de Transport d’Électricité (RTE), Paris, France

Abstract

Generative models have recently emerged as powerful surrogates for physical systems, demonstrating increased accuracy, stability, and/or statistical fidelity. However, most approaches rely on iteratively denoising a Gaussian, a choice that may not be the most effective for autoregressive prediction tasks, where the current and future states are often closely related. We therefore benchmark generative models based on stochastic interpolants, which can learn maps between arbitrary densities, against standard Gaussian-denoising frameworks across a range of fluid and climate systems. Following prior work, we consider a transport map for dynamical systems that learns an interpolant between a point mass at the current state and a conditional distribution of future states. We find that stochastic interpolants can match or outperform Gaussian-denoising baselines in pointwise accuracy, spectral fidelity, and probabilistic skill. Furthermore, we identify a tradeoff where deterministic sampling can improve pointwise accuracy but smooth predictions, whereas stochastic sampling recovers spectral content and calibration but requires more function evaluations, as well as ensemble averaging to recover pointwise accuracy. As a whole, these results establish stochastic interpolants as a competitive baseline for generative physical emulation, and also indicate that the training loss, sampler, and transport map should be chosen with the physical system and target metric in mind.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. StocBench: A Benchmark for Generative Modeling of Stochastic Dynamics

    Aug 23, 2026Sebastian Pfister, Benjamin Holzschuh, Nils ThuereyGenerative ModelingProbabilistic Forecasting

  2. Generative Modeling via Kernelized Stochastic Interpolants

    Feb 23, 2026Florentin Coeurdoux, Etienne Lempereur, Nathanaël Cuvelle-Magar +2Stochastic Differential EquationsStochastic Interpolants

  3. TRIE: An Evaluation Framework for Stochastic PDE Surrogates

    Jun 30, 2026Bharat Srikishan, Javier E. Santos, Nikhil Muralidhar +1PDE Surrogate ModelingProbabilistic Forecasting