Metraipolis › archive › dc_8d249ef80b77

X-World 1.6: Building Controllable Virtual Cities with World Models — arXiv:2611.00596

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00596
License (as archived)
CC0-1.0
Archived
2026-11-03T10:30:56.203Z
SHA-256 of the archived text
107b2f33a65d3891a9901b0b5c6981131ef97dafabd816fd43c0f39301953a5e
Stable URL of this page
https://metraipolis.com/documento/dc_8d249ef80b77

How to cite

X-World 1.6: Building Controllable Virtual Cities with World Models — arXiv:2611.00596 — arXiv (en), https://arxiv.org/abs/2611.00596 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d249ef80b77 (Metraipolis archive dc_8d249ef80b77, sha256 107b2f33a65d3891a9901b0b5c6981131ef97dafabd816fd43c0f39301953a5e)
BibTeX
@misc{dc8d249ef80b77,
  title = {X-World 1.6: Building Controllable Virtual Cities with World Models — arXiv:2611.00596},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00596},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d249ef80b77; sha256 107b2f33a65d3891a9901b0b5c6981131ef97dafabd816fd43c0f39301953a5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00596. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents \emph{X-World~1.6}, advancing X-World~1.0 toward a more reliable and versatile driving simulator. The upgraded base model offers finer-grained control over traffic semantics, including traffic lights and road markings, together with improved spatial consistency across cameras. Virtual City capabilities broaden scenario construction through a family of models conditioned on diverse 2D and 3D references, including support for generating multi-camera future videos from a single image. An enhanced post-training framework enables efficient causal, few-step generation with stronger temporal coherence, better quality retention over longer rollouts, and improved alignment with human preferences. We also introduce a dedicated evaluation suite to support systematic assessment and guide model iteration. Together, these upgrades expand the scenarios X-World can simulate and improve the efficiency and reliability of its generated observations, supporting broader use in autonomous-driving development.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.00596 — 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 2026-11-03T10:29:48.461Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).