arXiv AI July 2, 2026 By Alaina Kolli, Theodoros Xenakis, Utkarsh Utkarsh, Pengfei Cai, Rafael Gomez-Bombarelli, Alan Edelman, Christopher Vincent Rackauckas

SNAP-FM: Sparse Nonlinear Accelerated Projection for Physics-Constrained Generative Modeling

Read the original on arXiv AI →

arXiv:2607. 00095v1 Announce Type: cross Abstract: Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

1d ago

PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation

arXiv:2609.40287v1 Announce Type: new Abstract: Physics-constrained generative models aim to generate physical fields that match a target distribution and satisfy prescribed constraints. However, enf...

By Zhangyong Liang, Haibin Ling

efficiency benchmarks

arXiv Machine Learning

Jul 27

Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers

arXiv:2607. 22004v1 Announce Type: new Abstract: Energy natural gradient descent (ENGD) aligns parameter updates with the curvature of an underlying function-space energy, but existing formulations assume an unconstrained Euclidean parameter domain.

By Zhangyong Liang, Huanhuan Gao

benchmarks

arXiv AI

Jun 16

Separable Neural Architectures as Physical World Models: from Mathematical Theory to Applications

arXiv:2606. 14934v1 Announce Type: cross Abstract: This work introduces the Separable Neural Architecture (SNA), a function representational class combining neural approximation with tensor decomposition.

By Reza T Batley, Andrew Kichline, Sourav Saha

safety

arXiv AI

Jul 1

Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems

arXiv:2508. 09156v3 Announce Type: replace-cross Abstract: We present a framework for fine-tuning flow-matching generative models to enforce physical constraints and solve inverse problems in scientific systems.

By Jan Tauberschmidt, Sophie Fellenz, Sebastian J. Vollmer, Andrew B. Duncan

fine-tuning benchmarks

arXiv Machine Learning

3d ago

Tensor-Train Compressed Separable PINNs: A Curvature-Aware Optimization Framework for Parametric PDEs in High Dimensions

arXiv:2609.36165v1 Announce Type: cross Abstract: In this work, we develop a second-order optimization framework for physics-informed neural networks (PINNs) applied to high-dimensional parametric pa...

By Denis Korolev, Martin Eigel

arXiv Machine Learning

Jun 2

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing

arXiv:2604. 17838v2 Announce Type: replace Abstract: Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.

By Kijung Jeon, Michael Muehlebach, Molei Tao

diffusion robotics benchmarks safety

One email a morning, machine-written

Related stories

PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation

Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solvers

Separable Neural Architectures as Physical World Models: from Mathematical Theory to Applications

Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems

Tensor-Train Compressed Separable PINNs: A Curvature-Aware Optimization Framework for Parametric PDEs in High Dimensions

Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing