Metraipolis › archive › dc_1df667ab514b

VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation — arXiv:2609.33464

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.33464
License (as archived): CC0-1.0
Archived: 2026-10-08T00:17:08.876Z
SHA-256 of the archived text: 4782a192e7411414a4424160e9a51f6374d60a25240ac380918d0ee9aec628da
Stable URL of this page: https://metraipolis.com/documento/dc_1df667ab514b

How to cite

VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation — arXiv:2609.33464 — arXiv (en), https://arxiv.org/abs/2609.33464 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1df667ab514b (Metraipolis archive dc_1df667ab514b, sha256 4782a192e7411414a4424160e9a51f6374d60a25240ac380918d0ee9aec628da)

BibTeX

@misc{dc1df667ab514b,
  title = {VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation — arXiv:2609.33464},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33464},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1df667ab514b; sha256 4782a192e7411414a4424160e9a51f6374d60a25240ac380918d0ee9aec628da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33464. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World models learn internal representations of environment dynamics to predict future states, enabling agents to optimize action plans without physical interactions. However, developing world models that genuinely internalize underlying causal physical laws to explicitly reason about action preconditions and subsequent state transitions remains an open challenge. In this paper, we propose VIDEAS, a data distillation framework that transforms continuous physical dynamics from operational videos into explicit action semantics for foundation models. Specifically, it deconstructs visual demonstrations into discrete action trajectories and utilizes advanced vision-language models (VLMs) to extract structured knowledge encapsulating action preconditions and effects. To ensure physical consistency, we introduce a prior-guided trajectory simulation mechanism grounded within a text-based environment to rigorously validate the extracted knowledge. Notably, we incorporate negative trajectories to enrich knowledge completeness and enhance data diversity to mitigate cognitive bias. Furthermore, we present VIDEAS-WM, an 8B/9B-parameter suite of language-based world models trained on 34K high-quality samples derived from AgiBot-World dataset. Extensive experiments demonstrate that VIDEAS-WM establishes state-of-the-art performance in high-level embodied action semantic reasoning, exhibiting profound physical understanding and robust generalization across unseen scenarios.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.33464 — 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 2026-10-07T23:52:16.474Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).