Related papers: Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing

Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing

URL: http://arxiv.org/abs/2604.07366v1
Date: Thu, 02 Apr 2026 02:56:29 GMT
Title: Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing
Abstract summary: Partial differential equations govern nearly every physical process in science and engineering, yet solving them at scale remains prohibitively expensive.<n>We argue that the core issue is the abstraction used to train learned solvers. Many models are asked to predict states, while many scientific settings require modeling how uncertainty moves through constrained dynamics.<n>This motivates emphflow learners: models that parameterize transport vector fields and generate trajectories through integration, echoing the continuous dynamics that define PDE evolution.
Score: 21.18315999355946
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Partial differential equations (PDEs) govern nearly every physical process in science and engineering, yet solving them at scale remains prohibitively expensive. Generative AI has transformed language, vision, and protein science, but learned PDE solvers have not undergone a comparable shift. Existing paradigms each capture part of the problem. Physics-informed neural networks embed residual structure, yet they are often difficult to optimize in stiff, multiscale, or large-domain regimes. Neural operators amortize across instances, yet they commonly inherit a snapshot-prediction view of solving and can degrade over long rollouts. Diffusion-based solvers model uncertainty, yet they are often built on a solver template that still centers on state regression. We argue that the core issue is the abstraction used to train learned solvers. Many models are asked to predict states, while many scientific settings require modeling how uncertainty moves through constrained dynamics. The relevant object is transport over physically admissible futures. This motivates \emph{flow learners}: models that parameterize transport vector fields and generate trajectories through integration, echoing the continuous dynamics that define PDE evolution. This physics-to-physics alignment supports continuous-time prediction, native uncertainty quantification, and new opportunities for physics-aware solver design. We explain why transport-based learning offers a stronger organizing principle for learned PDE solving and outline the research agenda that follows from this shift.

Related papers

PhysiFormer: Learning to Simulate Mechanics in World Space [56.16644631495]
We present PhysiFormer, a diffusion transformer for physically-plausible 3D object motion.<n>It represents objects as 3D meshes expressed in world coordinates.<n>It substantially outperforms autoregressive baselines in trajectory accuracy, rigidity preservation, and momentum-based physical consistency.
arXiv Detail & Related papers (2026-06-25T17:59:00Z)
Text2PDE: Latent Diffusion Models for Accessible Physics Simulation [7.16525545814044]
We introduce several methods to apply latent diffusion models to physics simulation.<n>We show that the proposed approach is competitive with current neural PDE solvers in both accuracy and efficiency.<n>By introducing a scalable, accurate, and usable physics simulator, we hope to bring neural PDE solvers closer to practical use.
arXiv Detail & Related papers (2024-10-02T01:09:47Z)
Masked Autoencoders are PDE Learners [7.136205674624813]
Masked pretraining can consolidate heterogeneous physics to learn rich latent representations.<n>We show that learned representations can generalize to a limited set of unseen equations or parameters.<n>We hope that masked pretraining can emerge as a unifying method across large, unlabeled, and heterogeneous datasets.
arXiv Detail & Related papers (2024-03-26T14:17:01Z)
Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics [97.38308257547186]
Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and material models. We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned. We introduce a new framework termed "Neural Constitutive Laws" (NCLaw) which utilizes a network architecture that strictly guarantees standard priors.
arXiv Detail & Related papers (2023-04-27T17:42:24Z)
KoopmanLab: machine learning for solving complex physics equations [7.815723299913228]
We present KoopmanLab, an efficient module of the Koopman neural operator family, for learning PDEs without analytic solutions or closed forms. Our module consists of multiple variants of the Koopman neural operator (KNO), a kind of mesh-independent neural-network-based PDE solvers. The compact variants of KNO can accurately solve PDEs with small model sizes while the large variants of KNO are more competitive in predicting highly complicated dynamic systems.
arXiv Detail & Related papers (2023-01-03T13:58:39Z)
Learning to Solve PDE-constrained Inverse Problems with Graph Networks [51.89325993156204]
In many application domains across science and engineering, we are interested in solving inverse problems with constraints defined by a partial differential equation (PDE) Here we explore GNNs to solve such PDE-constrained inverse problems. We demonstrate computational speedups of up to 90x using GNNs compared to principled solvers.
arXiv Detail & Related papers (2022-06-01T18:48:01Z)
Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations [62.81701992551728]
We present a physics-informed framework for solving time-dependent partial differential equations. Our model utilizes discrete cosine transforms to encode spatial and recurrent neural networks. We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations.
arXiv Detail & Related papers (2022-02-24T20:46:52Z)
Message Passing Neural PDE Solvers [60.77761603258397]
We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
arXiv Detail & Related papers (2022-02-07T17:47:46Z)
AdjointNet: Constraining machine learning models with physics-based codes [0.17205106391379021]
This paper proposes a physics constrained machine learning framework, AdjointNet, allowing domain scientists to embed their physics code in neural network training. We show that the proposed AdjointNet framework can be used for parameter estimation (and uncertainty quantification by extension) and experimental design using active learning.
arXiv Detail & Related papers (2021-09-08T22:43:44Z)
Encoding physics to learn reaction-diffusion processes [18.187800601192787]
We show how a deep learning framework that encodes given physics structure can be applied to a variety of problems regarding the PDE system regimes. The resultant learning paradigm that encodes physics shows high accuracy, robustness, interpretability and generalizability demonstrated via extensive numerical experiments.
arXiv Detail & Related papers (2021-06-09T03:02:20Z)
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
arXiv Detail & Related papers (2021-04-07T17:59:23Z)

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