TensorX
返回文献探索

Paper · arXiv 2512.00425

What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

Minh-Quan Le, Yuanzhi Zhu, Vicky Kalogeiton, Dimitris Samaras

54 upvotesNovember 29, 2025arXiv 预印本
AI 摘要

A physics-grounded post-training framework using verifiable rewards improves physical realism and motion quality in video diffusion models.

video diffusion modelsNewtonRewardsverifiable rewardsoptical flowhigh-level appearance featuresNewtonian kinematic constraintmass conservation rewardNewtonian Motion PrimitivesNewtonBench-60Kphysics plausibilitymotion smoothnesstemporal coherence

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 NewtonRewards, the first physics-grounded post-training framework for video generation based on verifiable rewards. Instead of relying on human or VLM feedback, NewtonRewards extracts 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 NewtonRewards on five Newtonian Motion Primitives (free fall, horizontal/parabolic throw, and ramp sliding down/up) using our newly constructed large-scale benchmark, NewtonBench-60K. Across all primitives in visual and physics metrics, 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.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards | TensorX