Metraipolis › archive › dc_d04e4f19bfe4

Cycle WAM: Coupling Action and Video through Cycle Consistency — arXiv:2611.04711

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04711
License (as archived)
CC0-1.0
Archived
2026-11-04T18:36:48.498Z
SHA-256 of the archived text
258c770aa87283b290fe7030538dc5d9e8bd8cb274aab83dd866e9f23c58a860
Stable URL of this page
https://metraipolis.com/documento/dc_d04e4f19bfe4

How to cite

Cycle WAM: Coupling Action and Video through Cycle Consistency — arXiv:2611.04711 — arXiv (en), https://arxiv.org/abs/2611.04711 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d04e4f19bfe4 (Metraipolis archive dc_d04e4f19bfe4, sha256 258c770aa87283b290fe7030538dc5d9e8bd8cb274aab83dd866e9f23c58a860)
BibTeX
@misc{dcd04e4f19bfe4,
  title = {Cycle WAM: Coupling Action and Video through Cycle Consistency — arXiv:2611.04711},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04711},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d04e4f19bfe4; sha256 258c770aa87283b290fe7030538dc5d9e8bd8cb274aab83dd866e9f23c58a860},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04711. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. The underlying link is causal: robot actions produce changes in the scene, and video observations of these changes provide evidence for inferring the actions that produced them. However, existing training formulations do not by themselves ensure that actions and their predicted visual consequences are consistent, potentially limiting the use of pretrained capabilities. We treat video and action as paired modalities linked by this causal relationship and learn their correspondence through a unified training framework designed to better exploit pretrained video priors. Cycle WAM first augments video-action co-training with bidirectional conversion to reinforce cross-modal correspondence and recover forward and inverse dynamics. It then introduces a differentiable cycle-reconstruction objective to further couple the two mappings. The resulting model supports both forward and inverse dynamics, with the potential to improve performance through more effective use of pretrained video priors. Cycle WAM achieves state-of-the-art performance among comparable methods on LIBERO-Pro and substantially improves DreamZero on DROID. Comparisons with UWM characterize its inverse-dynamics performance and show sharper visual detail in the displayed forward-dynamics predictions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.04711 — 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 2026-11-04T18:32:37.461Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).