Metraipolis › archive › dc_edd4f7ed2a56

Long-WAM: Scaling the Context of World-Action Models — arXiv:2610.10528

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10528
License (as archived)
CC0-1.0
Archived
2026-10-08T11:12:12.423Z
SHA-256 of the archived text
134ae4d524a15db64fc3fc8dd3edc81cdd88bcd882f85711f2f7c0d3e7d738d8
Stable URL of this page
https://metraipolis.com/documento/dc_edd4f7ed2a56

How to cite

Long-WAM: Scaling the Context of World-Action Models — arXiv:2610.10528 — arXiv (en), https://arxiv.org/abs/2610.10528 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edd4f7ed2a56 (Metraipolis archive dc_edd4f7ed2a56, sha256 134ae4d524a15db64fc3fc8dd3edc81cdd88bcd882f85711f2f7c0d3e7d738d8)
BibTeX
@misc{dcedd4f7ed2a56,
  title = {Long-WAM: Scaling the Context of World-Action Models — arXiv:2610.10528},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10528},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edd4f7ed2a56; sha256 134ae4d524a15db64fc3fc8dd3edc81cdd88bcd882f85711f2f7c0d3e7d738d8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10528. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action models under real-time control constraints. Our central finding is that access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively (AR). We first learn causal prediction from robot and egocentric videos without action labels, then preserve this history-to-future structure during world-action adaptation. On RoboCasa GR-1, increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7%, whereas a bidirectionally pretrained initialization shows no net gain; robot-domain AR pretraining further raises peak success on GR-1 and LIBERO-Long. Long-WAM also achieves the best results among compared methods on LIBERO-Long, RoboTwin 2.0, and DOMINO. Streaming observation encoding, asynchronous execution, and hardware-specific acceleration enable deployment on RTX 5090, DGX Spark, and Jetson AGX Thor without dropping future prediction; on RTX 5090, each action chunk, including future-video latent prediction, takes 107.4 ms. Real-time deployment on Unitree G1 and YAM supports dynamic and long-horizon manipulation, including 95% success on dynamic cup stacking, where Pi0.5 and Fast-WAM succeed in none of 20 trials. As a memory-informed executor, Long-WAM also complements higher-level planning in composite tasks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.10528 — 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 2026-10-08T10:14:06.189Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).