
Veo 3: Emergent Zero‑Shot Video Intelligence Toward Vision Foundation Models
105
Veo 3’s emergent zero-shot skills across perception, physics, manipulation, and reasoning point to video models becoming generalist vision foundation models.
The ability of AI models to perform tasks they were not explicitly trained on, demonstrating emergent generalization from broad pretraining.

Veo 3’s emergent zero-shot skills across perception, physics, manipulation, and reasoning point to video models becoming generalist vision foundation models.