Metraipolis › archive › dc_34faffad06dc

InternW0: A Foundational Physical World Model for Efficient Real-World Interactions — arXiv:2609.27656

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27656
License (as archived)
CC0-1.0
Archived
2026-10-08T09:12:53.502Z
SHA-256 of the archived text
f1ae9f304e0ddf043d84c2ede59d88433acf47080c49d3c8346ca89b1566926e
Stable URL of this page
https://metraipolis.com/documento/dc_34faffad06dc

How to cite

InternW0: A Foundational Physical World Model for Efficient Real-World Interactions — arXiv:2609.27656 — arXiv (en), https://arxiv.org/abs/2609.27656 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_34faffad06dc (Metraipolis archive dc_34faffad06dc, sha256 f1ae9f304e0ddf043d84c2ede59d88433acf47080c49d3c8346ca89b1566926e)
BibTeX
@misc{dc34faffad06dc,
  title = {InternW0: A Foundational Physical World Model for Efficient Real-World Interactions — arXiv:2609.27656},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27656},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_34faffad06dc; sha256 f1ae9f304e0ddf043d84c2ede59d88433acf47080c49d3c8346ca89b1566926e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27656. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physical intelligence requires more than predicting how the world may evolve: predictions must remain actionable as the world continues to change. We introduce InternW0, the first instantiation of the InternW physical world model series from Shanghai AI Laboratory, built around omnimodal interfaces, asynchronous multi-frequency processing, and local physical modeling under partial observations and external influences. InternW0 jointly learns future visual dynamics and continuous robot control through an asymmetric video--action architecture with flow matching. A high-capacity video expert provides longer-horizon predictive context, while a lightweight action expert operates at a faster timescale. Instead of regenerating the future for every action update, InternW0 reuses layerwise K/V and adapts it to newly observed states through observation-conditioned context routing. Domain-specific interfaces and soft prompts support heterogeneous embodiments, while contact-aware post-training incorporates force and tactile signals for contact-rich manipulation. We train InternW0 on approximately 7,200 hours of heterogeneous robot and egocentric data, including EgoLab, a 275-hour real-laboratory egocentric dataset. Evaluation spans simulation benchmarks and real-world scientific tasks, including a 15-stage metal--organic framework synthesis workflow and 5-stage contact- and force-aware dexterous manipulation for general-purpose quantitative pipetting. These results advance scalable, asynchronous, and science-native physical world models for universal and efficient real-world interactions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.27656 — 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 2026-10-08T08:13:26.702Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).