Metraipolis › archive › dc_0f91fcbffca7

CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight — arXiv:2610.00859

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00859
License (as archived)
CC0-1.0
Archived
2026-10-06T19:11:51.401Z
SHA-256 of the archived text
40fa36cbd482b42c6b0912a52b5256995f7683a5fb12242893f091550fdf422e
Stable URL of this page
https://metraipolis.com/documento/dc_0f91fcbffca7

How to cite

CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight — arXiv:2610.00859 — arXiv (en), https://arxiv.org/abs/2610.00859 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f91fcbffca7 (Metraipolis archive dc_0f91fcbffca7, sha256 40fa36cbd482b42c6b0912a52b5256995f7683a5fb12242893f091550fdf422e)
BibTeX
@misc{dc0f91fcbffca7,
  title = {CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight — arXiv:2610.00859},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00859},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f91fcbffca7; sha256 40fa36cbd482b42c6b0912a52b5256995f7683a5fb12242893f091550fdf422e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00859. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video simultaneously, but such training paradigms introduce a mismatch: perturbed actions imply counterfactual future visual, while the noised video remains tied to the GT recording. In low-noise regime, the scene geometry and even the dynamic behavior remain clearly visible from the noisy future frames despite the added noise. We present CtrlWAM, which executes perturbed actions in a simulator and pairs them with their noised visual consequences for joint WAM learning. To accommodate the different denoising requirements of video and actions, we introduce warped video--action noise schedules that aim to keep visual layout responsive as action predictions evolve. We further extend the action interface from ego-only control to a variable number of agent streams, allowing a unified model to represent predicted or commanded futures for multiple agents. Driving experiments show more accurate action forecasts, closer agreement between generated video and actions, and better following of supplied commands; robotics experiments show stronger motion fidelity and controllability. Matched controls support the benefit of off-path renders for command following and manipulation fidelity. Together, these findings contribute to a more controllable world action model. Project page: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.00859 — 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 2026-10-06T17:37:36.707Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).