Metraipolis › archive › dc_396ebbd913d0

Stochastic World Models for Verifying Vision-Based Neural Feedback Systems — arXiv:2609.38120

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38120
License (as archived)
CC0-1.0
Archived
2026-10-07T16:24:30.480Z
SHA-256 of the archived text
258ae2d9287d58d58ac5fd7c7a05a3533fe2abeb9e9f64e3f1495911c68fa34c
Stable URL of this page
https://metraipolis.com/documento/dc_396ebbd913d0

How to cite

Stochastic World Models for Verifying Vision-Based Neural Feedback Systems — arXiv:2609.38120 — arXiv (en), https://arxiv.org/abs/2609.38120 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_396ebbd913d0 (Metraipolis archive dc_396ebbd913d0, sha256 258ae2d9287d58d58ac5fd7c7a05a3533fe2abeb9e9f64e3f1495911c68fa34c)
BibTeX
@misc{dc396ebbd913d0,
  title = {Stochastic World Models for Verifying Vision-Based Neural Feedback Systems — arXiv:2609.38120},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38120},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_396ebbd913d0; sha256 258ae2d9287d58d58ac5fd7c7a05a3533fe2abeb9e9f64e3f1495911c68fa34c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38120. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 more faithfully than GAN surrogates with up to 130 times as many parameters. To verify these surrogates, we develop a procedure that combines falsification, adaptive refinement, symbolic, and backward analyses. On an emergency braking benchmark with a GAN surrogate, our procedure resolves the entire state space, 38% of which the state-of-the-art verifier left unresolved. On the RGB version of the benchmark, where no verification results have previously been reported, our procedure resolves over 80% of the state space with a world model surrogate.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.38120 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.692Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).