Metraipolis › archive › dc_72dca9e453a3

Motus2: A Self-Evolving General World Model for Dexterous Manipulation — arXiv:2608.30237

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30237
License (as archived)
CC0-1.0
Archived
2026-10-17T07:52:30.232Z
SHA-256 of the archived text
8b69b46127db478d987641af4b3ffbe550b35a9f86cf44957be5b50876b5ce21
Stable URL of this page
https://metraipolis.com/documento/dc_72dca9e453a3

How to cite

Motus2: A Self-Evolving General World Model for Dexterous Manipulation — arXiv:2608.30237 — arXiv (en), https://arxiv.org/abs/2608.30237 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72dca9e453a3 (Metraipolis archive dc_72dca9e453a3, sha256 8b69b46127db478d987641af4b3ffbe550b35a9f86cf44957be5b50876b5ce21)
BibTeX
@misc{dc72dca9e453a3,
  title = {Motus2: A Self-Evolving General World Model for Dexterous Manipulation — arXiv:2608.30237},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30237},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72dca9e453a3; sha256 8b69b46127db478d987641af4b3ffbe550b35a9f86cf44957be5b50876b5ce21},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30237. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output head to a world simulator, without coupling them into a closed decision-and-learning loop for policy improvement. We present Motus2, a self-evolving general world model for dexterous manipulation. Motus2 advances world modeling through model scaling and data scaling. For model scaling, a single model with shared weights exposes three control interfaces: a policy (world-action model), a simulator (action-conditioned world model), and an evaluator (value model). The policy proposes candidate action chunks, the simulator predicts their visual consequences, and the evaluator assesses the predicted outcomes. Their coupling forms a closed decision-and-learning loop for policy improvement. This formulation uses curated expert demonstrations for action learning, while failed and suboptimal interactions provide valuable evidence for dynamics modeling and value learning. For data scaling, Motus2 progresses from large-scale monocular egocentric data to synchronized stereo egocentric data, followed by robot-domain adaptation with robot trajectories and supplementary human-robot alignment data. Motus2 further studies global-autoregressive and hybrid-memory extensions of its sliding-window context, adds tactile feedback for contact-aware control, and is instantiated on a fully biomimetic platform with stereo vision, dual arms, dual dexterous hands, and tactile sensing. Together, egocentric data scaling and closed-loop general world model scaling provide a general path toward self-evolving dexterous manipulation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.30237 — 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 2026-10-17T07:28:26.839Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).