AI 视频模型终于学会物理规律了
现在的视频生成模型只会照着像素画下一帧，画面好看但不懂物理——你让它预测一个球怎么滚，它可能画出球穿墙而过。这篇论文换了个思路：不直接学像素，而是把运动拆成「低阶规律 + 高阶修正」，在结构化的隐空间里做数值积分，让模型只负责补上那些复杂的残余项。结果在 5 个物理任务(匀速、抛物线、碰撞、弹跳、逼近)上，它学到的规律能外推到训练分布之外：比如只见过红球从左往右，它能正确预测蓝方块从右往左；而且参数少了 26 倍，速度快了 143 倍。这是第一个能真正外推物理规律的视频世界模型。它不是你明天能用上的东西，但它是视频生成从「画得像」走向「懂规律」的关键一步。
📄 原文摘要(英文)
The world evolves following its dynamics, i.e., its laws of motion. However, leading video diffusion models largely fit the pixels without modeling how the pixels transit over time. Thus, they render visually plausible frames but may not accurately obey the laws. To capture the dynamics purely from pixels, we introduce Latent Dynamics Reasoning (LDR). LDR casts the latent transition as an explicit kinematic integration, where the lower-order dynamics are integrated numerically and the model regresses only the third- and higher-order residual that drives the rollout. For this integration to extrapolate better, LDR runs it on a structured latent rather than dense convolutional features. Following PhyWorld, we validate LDR on a controlled white-box physics benchmark spanning five tasks (uniform motion, parabola, collision, bouncing, looming), focusing on out-of-distribution scenarios that reveal whether a model has truly learned the underlying dynamics. LDR extrapolates the learned dynamics far better: the gap between its in- and out-of-distribution error is over 20times smaller than the video diffusion baseline's, under both single- and joint-task training at 256^2 resolution, while using 26times fewer parameters and running 143times faster. LDR can even generalize under severe shift: for example, trained only on red balls moving left-to-right, it correctly predicts the motion of a blue square moving right-to-left. To our knowledge, this is the first video world model that extrapolates learned dynamics beyond its training distribution. Project page: https://lat-dyn-reason.github.io/