ProPhy: Progressive Physical Alignment for Dynamic World Simulation

TL;DR

ProPhy introduces a two-stage physics-aware video generation framework that enhances physical consistency and dynamic realism by explicitly modeling physical principles and alignment.

Contribution

It proposes a novel Progressive Physical Alignment framework with a Mixture-of-Physics-Experts mechanism for explicit physics-aware conditioning in video synthesis.

Findings

ProPhy outperforms existing methods on physics-aware video generation benchmarks.

The model produces more realistic and physically coherent dynamic videos.

Explicit physical alignment improves the fidelity of complex physical phenomena in generated videos.

Abstract

Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex dynamics. This limitation arises primarily because existing approaches respond isotropically to physical prompts and neglect the fine-grained alignment between generated content and localized physical cues. To address these challenges, we propose ProPhy, a Progressive Physical Alignment Framework that enables explicit physics-aware conditioning and anisotropic generation. ProPhy employs a two-stage Mixture-of-Physics-Experts mechanism for discriminative physical prior extraction, where Semantic Experts infer semantic-level physical principles from textual descriptions, and Refinement Experts capture token-level physical dynamics. This mechanism allows the model to learn fine-grained, physics-aware video representations that better reflect underlying physical laws. Furthermore, we introduce a physical alignment strategy that transfers the physical reasoning capabilities of vision-language models into the Refinement Experts, facilitating a more accurate representation of dynamic physical phenomena. Extensive experiments on physics-aware video generation benchmarks demonstrate that ProPhy produces more realistic, dynamic, and physically coherent results than existing state-of-the-art methods.