SOURCE-LINKED INTELLIGENCE
Rethinking Video Autoencoders for Interactive World Models
Video world models predict future frames from past frames and actions. They serve as simulators in which agents train, plan or are evaluated, and that humans can control interactively. They generate in the latent space of a video autoencoder, whose compression sets their cost per frame and how long each action waits to take effect. Yet world models often reuse the autoencoders of text-to-video generators, built for offline generation with no agent waiting and, without their training data and code, not retrainable at another compression. We therefore ask how, where and how much a world model sh
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-21T17:58:11.000Z
First collected: 2026-10-22T08:52:46.617Z. This is not the publication date.