Metraipolis › archive › dc_ebef75a8a87e

WorldCast: Exploring Intelligent Visual Generation in World State Prediction — arXiv:2610.20731

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.20731
License (as archived): CC0-1.0
Archived: 2026-10-16T09:06:15.520Z
SHA-256 of the archived text: 7769dfe999e49b5b17bebfd0a7faffde7dc792cc3b2cee9d51d4a5a843418aef
Stable URL of this page: https://metraipolis.com/documento/dc_ebef75a8a87e

How to cite

WorldCast: Exploring Intelligent Visual Generation in World State Prediction — arXiv:2610.20731 — arXiv (en), https://arxiv.org/abs/2610.20731 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebef75a8a87e (Metraipolis archive dc_ebef75a8a87e, sha256 7769dfe999e49b5b17bebfd0a7faffde7dc792cc3b2cee9d51d4a5a843418aef)

BibTeX

@misc{dcebef75a8a87e,
  title = {WorldCast: Exploring Intelligent Visual Generation in World State Prediction — arXiv:2610.20731},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20731},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebef75a8a87e; sha256 7769dfe999e49b5b17bebfd0a7faffde7dc792cc3b2cee9d51d4a5a843418aef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20731. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humans interpret multimodal observations of the world and forecast how it will evolve. Recent multimodal generative systems have demonstrated similar capabilities: they can integrate multimodal context and synthesize visual outputs that depict changes in the world. To characterize this emerging trajectory, we organize model capabilities into a four-level hierarchy and discover that higher-level tasks remain relatively underexplored despite model progress. To bridge this gap, we explore model performance on multi-step world state prediction, a high-level task that requires models to forecast successive future world states from multimodal observations and diverse references. Such a task requires models to possess entangled understanding and generation capabilities, as well as extensive world knowledge to translate human action sequences, physical transformations, and abstract visual reasoning into coherent visual outputs. We introduce WorldCast, a benchmark comprising 320 manually designed cases across eight categories, and evaluate 12 representative models. The conducted experiments yield three key insights: (a) advances in frontier models are rapidly pushing the boundaries of intelligent world modeling, with the GPT-Image-2.5 System scoring 72.8 and demonstrating early-stage visual state prediction capabilities on real-world tasks; (b) WorldCast reveals substantial gaps between models: even Nano Banana Pro reaches only 42.8 and the best open-source model scores 20.1, with deficits in handling complex context, entangled references, and reasoning-heavy tasks; (c) strong generative models effectively draw on the capabilities of their underlying language models. These findings highlight the need for multimodal generative models that are capable of dynamic planning and reasoning while also being deeply unified to faithfully simulate real-world states.

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/2610.20731 — 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 2026-10-16T08:44:17.858Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).