Metraipolis › archive › dc_553489856780

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining — arXiv:2609.07398

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07398
License (as archived)
CC0-1.0
Archived
2026-10-16T15:31:07.164Z
SHA-256 of the archived text
426b0a9e6805263943f9c84006f6374e83042f27b109703b5346bb9727a92336
Stable URL of this page
https://metraipolis.com/documento/dc_553489856780

How to cite

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining — arXiv:2609.07398 — arXiv (en), https://arxiv.org/abs/2609.07398 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_553489856780 (Metraipolis archive dc_553489856780, sha256 426b0a9e6805263943f9c84006f6374e83042f27b109703b5346bb9727a92336)
BibTeX
@misc{dc553489856780,
  title = {OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining — arXiv:2609.07398},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07398},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_553489856780; sha256 426b0a9e6805263943f9c84006f6374e83042f27b109703b5346bb9727a92336},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07398. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World-Action Models inherit world knowledge from video-generative priors, and channel it into executable control signals through embodied experience. Existing systems, however, are monolithic: the generative backbone, visual representation, architecture, information flow, inference procedure, and training data are tightly coupled, obscuring which design choices matter and why. We introduce OpenWAM, an open research stack that turns world-action pretraining into a controlled experimental program. OpenWAM-Infra factorizes the WAM design space into composable modules with unified training, inference, deployment, and evaluation. On this substrate, OpenWAM-Study examines three questions through controlled experiments: what to inherit, how world and action learning interact, and how their synergy scales; and distills three principles: upstream knowledge transfers through a sufficiently capable generative backbone and a compact, information-rich latent space; world-action synergy requires dedicated action capacity, explicit world-to-action information flow, and synchronized joint denoising; and embodied pretraining principally improves out-of-domain generalization, with one-stage co-training over egocentric and robot data integrating world coverage and action grounding. Composing these principles, we build OpenWAM-{\alpha}, an open WAM pretrained on roughly 6,400 hours of egocentric human and robot data and evaluated across simulation and real-world benchmarks. Across the eight simulation benchmarks and the real-robot experiments, which together span embodiments from single-arm and bimanual manipulation to dexterous hands, OpenWAM-{\alpha} delivers consistently excellent performance, sustaining its top-tier standing from simulation to the physical world. We release the full stack, including infrastructure, evaluation protocols, pretrained models, and data recipes, to facilitate future research.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.07398 — 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 2026-10-16T15:11:47.584Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).