Metraipolis › archive › dc_63afe2dbed01

TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models — arXiv:2609.26314

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26314
License (as archived): CC0-1.0
Archived: 2026-10-08T13:47:04.999Z
SHA-256 of the archived text: efc21bc24e0fe6278d2218eb203616e5b180a4a36c333b7ef3c6f5bb49cd4c91
Stable URL of this page: https://metraipolis.com/documento/dc_63afe2dbed01

How to cite

TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models — arXiv:2609.26314 — arXiv (en), https://arxiv.org/abs/2609.26314 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63afe2dbed01 (Metraipolis archive dc_63afe2dbed01, sha256 efc21bc24e0fe6278d2218eb203616e5b180a4a36c333b7ef3c6f5bb49cd4c91)

BibTeX

@misc{dc63afe2dbed01,
  title = {TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models — arXiv:2609.26314},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26314},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63afe2dbed01; sha256 efc21bc24e0fe6278d2218eb203616e5b180a4a36c333b7ef3c6f5bb49cd4c91},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26314. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: the head view captures the overall task, while wrist views reveal local gripper-object interactions. However, evaluating these views independently cannot determine whether they describe the same action and object state. We introduce TRIWORLDBENCH, a benchmark for evaluating embodied world models through synchronized head, left-wrist, and right-wrist videos. It contains 500 episodes across 50 bimanual manipulation tasks and uses 19 metrics to assess tri-view consistency, task alignment, physical and 3D coherence, motion quality, temporal consistency, and visual quality. By combining cross-view checks with measurements tailored to each camera, the benchmark evaluates whether plausible individual videos also form a consistent prediction of the intended task. We summarize overall performance with TWB-Score and retain per-view results to identify where predictions fail. This extends world-model evaluation beyond single-view visual quality. Code, data, and metric definitions are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.26314 — 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 2026-10-08T13:18:38.305Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).