Glossary · Term

DINOv3

← all terms

Definition

Plain language

A large ready-made vision system that already understands objects, motion, and layout in ordinary images.

As stated in the literature

A self-supervised pretrained vision backbone whose frozen features provide a smooth, semantically structured latent space reused here as the world model's frame representation.

Also called: DINOv2, DINO

Why it matters: Reusing a ready-made vision system saves enormous training effort and gives other models a reliable understanding of images to build on.

For example, a new system can skip learning to recognize objects from scratch and instead reuse DINOv3's existing sense of what's in a picture.

Heard on the show

“They built it on top of DINOv3, a big frozen vision model pretrained on enormous amounts of ordinary images, which already understands objects, motion, and spatial layout.”
Episode 206 — How Four-Second Clips Become Hours of Playable AI Soccer

Mentioned in 1 episode

  1. 206
    How Four-Second Clips Become Hours of Playable AI Soccer

Related terms