Abstract
Recent video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistently-revealing a persistent gap between visual realism and physical realism. We propose $\texttt{NewtonRewards}$, the first physics-grounded post-training framework for video generation based on $\textit{verifiable rewards}$. Instead of relying on human or VLM feedback, $\texttt{NewtonRewards}$ extracts $\textit{measurable proxies}$ from generated videos using frozen utility models: optical flow serves as a proxy for velocity, while high-level appearance features serve as a proxy for mass. These proxies enable explicit enforcement of Newtonian structure through two complementary rewards: a Newtonian kinematic constraint enforcing constant-acceleration dynamics, and a mass conservation reward preventing trivial, degenerate solutions. We evaluate $\texttt{NewtonRewards}$ on five Newtonian Motion Primitives (free fall, horizontal/parabolic throw, and ramp sliding down/up) using our newly constructed large-scale benchmark, $\texttt{NewtonBench-60K}$. Across all primitives in visual and physics metrics, $\texttt{NewtonRewards}$ consistently improves physical plausibility, motion smoothness, and temporal coherence over prior post-training methods. It further maintains strong performance under out-of-distribution shifts in height, speed, and friction. Our results show that physics-grounded verifiable rewards offer a scalable path toward physics-aware video generation.
Abstract (translated)
最近的视频扩散模型能够生成视觉上吸引人的片段，但常常违背基本物理定律——物体漂浮、加速度异常以及碰撞行为不一致，这揭示了在视觉真实性和物理真实性之间存在着持续的差距。我们提出了$\texttt{NewtonRewards}$，这是一种基于可验证奖励的首个物理基础视频生成后训练框架。与依赖人类或VLM（视觉语言模型）反馈不同，$\texttt{NewtonRewards}$使用冻结的效用模型从生成的视频中提取可测量的代理：光流作为速度的代理，而高级外观特征则作为质量的代理。这些代理能够通过两种互补奖励明确地强制执行牛顿结构：一种是强制恒定加速度动力学的牛顿运动约束奖励，另一种则是防止简单退化解的质量守恒奖励。 我们在五个牛顿运动原语（自由落体、水平/抛物线投掷以及斜坡上下滑动）上评估了$\texttt{NewtonRewards}$，使用我们新构建的大规模基准$\texttt{NewtonBench-60K}$。在所有原始数据的视觉和物理指标中，$\texttt{NewtonRewards}$始终改善了物理合理性、运动平滑度以及时间一致性，在先前的后训练方法之上表现优异。它还能够在外部分布（如高度、速度和摩擦力变化）下保持强大的性能。 我们的结果表明，基于物理学的可验证奖励为实现物理感知视频生成提供了一条可扩展的道路。
URL
https://arxiv.org/abs/2512.00425
