Physics-Informed Generative Modeling

Overview

The field develops models that generate distributions of physical fields, trajectories, images, and structures while respecting equations, conservation laws, geometry, or sensor physics. Common approaches include diffusion and flow matching with PDE-residual losses, constraint-preserving projections or manifold parameterizations, differentiable simulators, and physics-guided inference. Applications range from PDE inverse problems and uncertainty estimation to weather forecasting, medical imaging, materials design, molecular modeling, and physically plausible video. A central challenge is balancing physical validity with fidelity to the data distribution: stronger constraints can introduce bias or reduce diversity, while uncertainty calibration, out-of-distribution performance, and sampling cost remain important tests.

Latest papers

CardsList

122 papers14 papers in the last four weeks, down 46% on the four weeks before. 0.1% of all new papers.

  1. PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM

    May 22, 2025Siwei Meng, Yawei Luo, Ping LiuPhysics-Informed Generative ModelingPhysical Consistency in Video Generation

  2. Hessian-Informed Flow Matching

    Oct 15, 2024Christopher Iliffe Sprague, Mert Can Kurucu, Riccardo Tedoldi +3Flow MatchingPhysics-Informed Generative Modeling