Metraipolis › archive › dc_8c8181ec477f

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators — arXiv:2609.09155

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09155
License (as archived)
CC0-1.0
Archived
2026-10-16T15:12:35.014Z
SHA-256 of the archived text
ecf43c69f4d48e56dc953979bc2e7e67c15325a162933b01c3f5959a1ac7cb9f
Stable URL of this page
https://metraipolis.com/documento/dc_8c8181ec477f

How to cite

SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators — arXiv:2609.09155 — arXiv (en), https://arxiv.org/abs/2609.09155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8c8181ec477f (Metraipolis archive dc_8c8181ec477f, sha256 ecf43c69f4d48e56dc953979bc2e7e67c15325a162933b01c3f5959a1ac7cb9f)
BibTeX
@misc{dc8c8181ec477f,
  title = {SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators — arXiv:2609.09155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8c8181ec477f; sha256 ecf43c69f4d48e56dc953979bc2e7e67c15325a162933b01c3f5959a1ac7cb9f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-grained controllability with respect to low-level robot actions. A key obstacle to scaling such models in robotics is that actions are not a universal language in pixel space: changes in visual environment, camera view, robot placement, or embodiment alter how the same numerical action manifests visually, leading to conflicting supervision under mixed training and brittle generalization at deployment. We introduce SyncWorld, an action-conditioned world model that serves as a zero-shot simulator across unseen environments without any additional training. SyncWorld leverages a visual calibration episode---paired frames and actions that showcase all the controllable degrees of freedom---to specify the setup-specific Action--Visual Mapping in context. Training with visual calibration contexts teaches the model to interpret actions through visual evidence and to leverage interaction history when explicit calibration is unavailable. Experiments show that SyncWorld can accurately simulate action outcomes in previously unseen settings, and that its capability of simulating rollouts enables test-time policy improvement without training.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.09155 — 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 2026-10-16T14:49:57.399Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).