Paper recorded by Signals 4 on 2026-10-21 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-21 on arXiv · recorded by Signals 4 on 2026-10-22
Category: cs.CV · 计算机视觉 · first seen 2026-10-22
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 gen