No AI summary available for this article.
Why It Matters
Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces, while remaining tractable for closed-loop analysis. Generative adversarial networks (GANs) have served as perception surrogates, but they are large, reproduce complex scenes poorly, and are hard to verify. We explore stochastic world models as a richer class of perception surrogates. We train a world model with physically grounded latents, built from operations that standard verifiers bound. It reproduces held-out frames mor...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.38120v1 · Indexed about 1 hour ago