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

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

May 22, 2025

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

Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequently produce implausible results such as momentum violations and object interpenetrations. Existing physics-aware approaches often rely on task-specific fine-tuning or supervised data, which limits their scalability and applicability. To address the challenge, we present PhyMAGIC, a training-free framework that generates physically consistent motion from a single image. PhyMAGIC integrates a pre-trained image-to-video diffusion model, confidence-guided reasoning via LLMs, and a differentiable physics simulator to produce 3D assets ready for downstream physical simulation without fine-tuning or manual supervision. By iteratively refining motion prompts using LLM-derived confidence scores and leveraging simulation feedback, PhyMAGIC steers generation toward physically consistent dynamics. Comprehensive experiments demonstrate that PhyMAGIC outperforms state-of-the-art video generators and physics-aware baselines, enhancing physical property inference and motion-text alignment while maintaining visual fidelity.
Oct 15, 2024

Hessian-Informed Flow Matching

Data from physical systems often concentrate near stable states corresponding to minima of an energy function. Around these states, the curvature of the energy landscape shapes the local covariance structure of the data, which is often highly anisotropic: small perturbations around a data point raise its energy more sharply in some directions than in others. However, standard flow matching commonly connects noise to target data through isotropic conditional paths that do not explicitly follow this physical structure. We introduce Hessian-Informed Flow Matching (HI-FM), which uses the energy Hessian at each data sample to encode this local curvature in the conditional probability paths used for training. By locally linearizing energy-driven dynamics, we derive anisotropic paths that move samples toward their targets at different rates in different directions, without changing the standard flow matching objective. We evaluate HI-FM through molecular generation on Hessian-QM9 and GEOM-Drugs, using SemlaFlow as a shared backbone. With Hessians calculated offline only for the training data, across both datasets, HI-FM improves the physical and geometric quality of generated molecules while maintaining comparable chemical validity. Under a matched optimizer-update budget, HI-FM trained with only 10%10\% of Hessian-QM9 achieves lower mean energy, strain, and bond-length W1W_1 than the full-data SemlaFlow baseline. The results support local energy curvature as a useful inductive bias for flow matching.