Metraipolis › archive › dc_2732cf751d48

EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models — arXiv:2611.06748

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06748
License (as archived)
CC0-1.0
Archived
2026-11-05T18:18:07.769Z
SHA-256 of the archived text
69b5219f812e775516cf2f2706802c903f806f473fca595a32170cae7459143e
Stable URL of this page
https://metraipolis.com/documento/dc_2732cf751d48

How to cite

EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models — arXiv:2611.06748 — arXiv (en), https://arxiv.org/abs/2611.06748 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2732cf751d48 (Metraipolis archive dc_2732cf751d48, sha256 69b5219f812e775516cf2f2706802c903f806f473fca595a32170cae7459143e)
BibTeX
@misc{dc2732cf751d48,
  title = {EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models — arXiv:2611.06748},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06748},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2732cf751d48; sha256 69b5219f812e775516cf2f2706802c903f806f473fca595a32170cae7459143e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06748. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve. Coherent world evolution requires more than visual fidelity: when an event occurs, a model must infer its consequences for the entities in the world and then render the resulting state. For example, after a wild beast appears, the model should not only depict the wild beast, but also infer whether a nearby person should flee, take cover, or fight back based on the realized scene. Existing diffusion-based video models lack an explicit mechanism for maintaining world state and reasoning over such event-conditioned consequences, often producing visually plausible but behaviorally static or causally inconsistent outputs. To make this reasoning gap concrete and measurable, we propose a new problem, Out-of-Sight Causal Evolution, which requires a model to render an event, reason about its consequences for the evolving world state, and reveal a causally plausible outcome as the world continues to evolve, even out of sight. As a baseline reference solution, we introduce EvoWorld, a brain-renderer collaboration framework in which a vision-language model serves as the world brain: it observes generated segments, maintains an evolving account of the world, and reasons about plausible state transitions, while a segment-autoregressive video renderer realizes them visually. We further introduce EvoWorld-Data and EvoWorld-Bench for training and evaluating event realization, causal reactions, and revisit consistency. Experiments show that EvoWorld substantially improves event-conditioned causal evolution over recent models while preserving visual quality and consistency, establishing a reference point for reasoning-guided, autonomous world evolution beyond the current field of view.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.06748 — 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 2026-11-05T18:12:49.067Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).