ProPhy：面向动态世界模拟的渐进式物理对齐
ProPhy: Progressive Physical Alignment for Dynamic World Simulation
将视觉语言模型的物理推理能力通过渐进式对齐迁移到视频生成模型中，并利用混合物理专家机制实现细粒度物理条件控制，为物理一致的视频生成提供了可复用的技术路径。
原文依据 ProPhy employs a two-stage Mixture-of-Physics-Experts (MoPE) mechanism for discriminative physical prior extraction
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期视频生成领域的进展在构建世界模拟器方面展现出显著潜力。然而，当前模型仍难以生成物理一致的结果，尤其是在处理大规模或复杂动力学时。这一局限主要源于现有方法对物理提示做出各向同性响应，且忽略了生成内容与局部物理线索之间的细粒度对齐。为解决这些挑战，我们提出 ProPhy，一种渐进式物理对齐框架，能够实现显式的物理感知条件控制与各向异性生成。ProPhy 采用两阶段混合物理专家（MoPE）机制进行判别式物理先验提取，其中语义专家从文本描述中推断语义级物理原理，精炼专家则捕捉词元级物理动力学。该机制使模型能够学习细粒度、物理感知的视频表示，从而更好地反映底层物理规律。此外，我们引入一种物理对齐策略，将视觉语言模型（VLM）的物理推理能力迁移至精炼专家，促进对动态物理现象更准确的表示。在物理感知视频生成基准上的大量实验表明，ProPhy 相比现有最优方法能生成更真实、动态且物理连贯的结果。
英文原文摘要 1456 字符
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 (MoPE) 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 (VLMs) 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.