cs.LGNov 4, 2026

Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching

Authors: Giuliano Galadini, Aurelio Uncini, Danilo Comminiello

Organizations: Department of Information Engineering, Electronics and Telecommunications, Sapienza University of Rome, Rome, Italy

Abstract

Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems. However, standard architectures remain purely statistically driven and agnostic to the underlying governing equations, often violating fundamental physical constraints during inference. Existing zero-shot approaches designed to enforce these constraints typically rely on rigid algebraic projections. While effective for sparse boundary conditions, applying such discrete geometric corrections to dense, full-domain PDEs may disrupt the probability path, \rev{potentially deviating from the learned manifold and introducing substantial computational overhead}. To address these challenges, we introduce Energy-Guided Transport, a novel training-free framework that formulates non-linear physical constraints as a smooth potential energy landscape. Rather than interrupting the ODE integration, our method applies a continuous dissipative force directly to the intermediate generative states, steering them toward the physical manifold. By evaluating this force implicitly via reverse-mode automatic differentiation, our framework preserves the natural dynamics of the flow while maintaining an efficient O(N)\mathcal{O}(N) algorithmic complexity. We extensively evaluate our framework across various 1D and 2D physical systems, including the chaotic Navier-Stokes equations. Our method achieves stable generation without structural divergence, significantly improves the stability-accuracy trade-off compared to state-of-the-art methods, and substantially accelerates inference with respect to exact projection strategies. Code available at: https://github.com/ispamm/Projection-free-energy-guided-flow-matching.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation

    Sep 29, 2025Jinhao Liang, Yixuan Sun, Anirban Samaddar +2Constrained Generative Modelingconstrained flow matching

  2. Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds

    Feb 19, 2026Noah Trupin, Rahul Ghosh, Aadi JangidConstrained Generative ModelingPhysics-Informed Diffusion Models

  3. Source Anchoring for Physical Consistency in Flow Matching Models

    Sep 27, 2026Giulia Romoli, Filippo Ruffini, Paolo SodaConstrained Generative ModelingPhysics-Informed Generative Modeling