Unverified50% confidenceFactExact time

In world models, the VAE typically compresses 64×64 pixel game frames into a 32-dimensional or 64-dimensional latent vector.

1

Sources

50%

Confidence

Long-term

Relevance

9/1/2026

First Seen

Sources

World Models Explained: How AI Learns to Make Decisions in Its Dreams

Related Entities

VAEconcept World Modelsconcept

Related Claims

VerifiedA raw video of 512×512 resolution and 24 frames has a data volume of approximately 18 MB, which is reduced to approximately 1/96 of the original after VAE compression into the 64×64×4 latent variable space.73% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/838273

API

curl https://kongchang.com/api/v1/knowledge/claims/838273

MCP

get_claim(id=838273)