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. Physically Admissible Generative Flow Matching for Sparse Flow Reconstruction

    Nov 17, 2026Yuhao Wang, Yuanxi PengPhysics-Informed Generative Modelingconstrained flow matching

  2. Manifold Attracting Flow Matching: Physics-Constrained Sampling via Continuous Geometric Dynamics

    Nov 12, 2026Guanyu Chen, Jinchen Wang, Shengze Xu +4constrained flow matchingConstrained Generative Modeling

  3. AdjointFlow: Accelerating Scientific Inverse Problems with Physics-Based Transport

    Nov 10, 2026Ethan Hanold, Nicholas M. Boffi, Qin Li +1Inverse ProblemsPhysics-Informed Generative Modeling

  4. Physically Guided TeX Generation for Low-Light Visual Tasks

    Nov 7, 2026Daoheng Li, Jianjun Qian, Mengkai Yan +1Physics-Informed Generative ModelingInfrared-Visible Image Fusion

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

    Nov 4, 2026Giuliano Galadini, Aurelio Uncini, Danilo ComminielloPhysics-Informed Generative ModelingConstrained Generative Modeling

  6. Physics-informed traditional and generative Mori-Zwanzig-reduced models for multiscale systems

    Nov 3, 2026Emily Williams, Saad Qadeer, Amanda Howard +1Reduced-Order ModelingMultiscale Time-Series Modeling

  7. Macrocanonical Generator Networks: Data-Efficient Neural Surrogates for Amortized Physics Simulation

    Nov 3, 2026Niall Jeffrey, Benjamin D. WandeltCosmologyNeural Surrogate Modeling

  8. Recovering Missing Degrees of Freedom in Simulation-Trained Field-Level Generative Models

    Nov 2, 2026Masato Shirasaki, Shiro IkedaPhysics-Informed Generative ModelingSimulation-Based Inference

  9. Physics-Guided Flow Matching: A Generative AI Framework for Global Total Electron Content Forecasting

    Oct 27, 2026Si-Tong Yang, Feng Ye, Xian Lu +2Spatiotemporal ForecastingPhysics-Informed Generative Modeling

  10. Estimating aerosol particle number size distributions from PM2.5 with physics-regularized flow matching

    Oct 24, 2026Zhi-Song Liu, Jenni Köykkä, Wenqing Peng +3Physics-Informed Generative ModelingAir Quality Prediction

  11. On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution

    Oct 23, 2026Yubo Ye, Maryam Toloubidokhti, Sumeet Vadhavkar +3Parameter IdentifiabilityPhysics-Informed Generative Modeling

  12. Inverse Modeling for Laser Pulse Shape Design in Inertial Confinement Fusion

    Oct 22, 2026Ricardo Luna Gutierrez, Vineet Gundecha, Rahman Ejaz +5Inertial Confinement FusionInverse Design

  13. PRISM: Learning Realistic Depth via Physics-Grounded Noise Disentanglement with Semantic-Geometric Collaboration

    Oct 21, 2026Xiujian Liang, Jiacheng Liu, Mingyang Sun +4Sim-to-Real TransferPhysics-Informed Generative Modeling

  14. Multi-View Structural Representations for Physically-Consistent TeX Generation

    Oct 19, 2026Daoheng Li, Jianjun Qian*, Mengkai Yan +1Image GenerationPhysics-Informed Generative Modeling

  15. Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process Posteriors

    Oct 15, 2026Tobias Weber, Carla Sagebiel, Philipp HennigGaussian ProcessesPhysics-Informed Generative Modeling

  16. When do explicit penalties improve flow matching?

    Oct 11, 2026Lea Kunkel, Alberto González-Sanz, Sophie LangerFlow MatchingConstrained Generative Modeling

  17. Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution

    Oct 10, 2026Haohan Zou, Alexander Scheinker, Yuanyuan ShiLatent Dynamics ModelingPhysics-Informed Generative Modeling

  18. MontageFlow: Physically Valid High Fidelity EEG Generation

    Oct 10, 2026Sudarshan Regmi, Nabaraj Subedi, Arvind Pillai +6EEG Signal GenerationTime Series Generation

  19. Temporal Diffusion Bridge Model for Vessel Extraction Using Physics-informed Synthetic Data

    Oct 8, 2026Jinkui Hao, Donald R. Cantrell, Ramez Abdalla +2Coronary Artery SegmentationCoronary Angiography

  20. Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery

    Oct 8, 2026Xun Chen, Weiyao Ke, Yu-Gang Ma +2Lattice Field TheoryHigh-Energy Physics

  21. From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators

    Oct 7, 2026Kerui Chen, Jianrong Zhang, Kai Lv +1Physics-Informed Generative ModelingDiffusion Models for Motion Generation

  22. One Frame, Full Heartbeat: ECG-Free 4D Cardiac Cine MRI Synthesis via Radial-Decomposed Flow Matching

    Oct 6, 2026Shiyi Wang, Ruochen Sun, Xiang Li +2Medical Image SynthesisCardiac MRI

  23. PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation

    Oct 6, 2026Guo Tang, Yongtao WangPhysics-Informed Generative ModelingTactile Sensing

  24. OCL-PDE: A Generative Framework for PDE Inverse Problems with Observation-Complementary Latents

    Oct 5, 2026Ding Yang, Chuqi Chen, Chang Ma +1Physics-Informed Generative ModelingPDE Operator Learning