# Improving the Physics of Video Generation with VJEPA-2 Reward Signal

arXiv: https://arxiv.org/abs/2510.21840 · HTML: https://mlsanity.com/paper/2510.21840/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 7 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 4 of 4)

- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)

## Built on by (most cited first, 4 of 4)

- [Interpreting Physics in Video World Models](https://mlsanity.com/paper/2602.07050/) (2026)
- [MIND-V: Hierarchical World Model for Long-Horizon Robotic Manipulation with RL-based Physical Alignment](https://mlsanity.com/paper/2512.06628/) (2025)
- [Physics-IQ Verified](https://mlsanity.com/paper/2606.18943/) (2026)
- [Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model](https://mlsanity.com/paper/2608.29904/) (2026)

## Abstract (arXiv)

This is a short technical report describing the winning entry of the PhysicsIQ Challenge, presented at the Perception Test Workshop at ICCV 2025. State-of-the-art video generative models exhibit severely limited physical understanding, and often produce implausible videos. The Physics IQ benchmark has shown that visual realism does not imply physics understanding. Yet, intuitive physics understanding has shown to emerge from SSL pretraining on natural videos. In this report, we investigate whether we can leverage SSL-based video world models to improve the physics plausibility of video generative models. In particular, we build ontop of the state-of-the-art video generative model MAGI-1 and couple it with the recently introduced Video Joint Embedding Predictive Architecture 2 (VJEPA-2) to guide the generation process. We show that by leveraging VJEPA-2 as reward signal, we can improve the physics plausibility of state-of-the-art video generative models by ~6%.