Metraipolis › archive › dc_fbab9f00fb88

From World Models to World Action Models: Rethinking Next-State Prediction — arXiv:2609.34414

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34414
License (as archived)
CC0-1.0
Archived
2026-10-08T00:17:23.441Z
SHA-256 of the archived text
1378b4febcc157ba7c59f711ad832386b8985bb679e4a95b8bfbd57159434e26
Stable URL of this page
https://metraipolis.com/documento/dc_fbab9f00fb88

How to cite

From World Models to World Action Models: Rethinking Next-State Prediction — arXiv:2609.34414 — arXiv (en), https://arxiv.org/abs/2609.34414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fbab9f00fb88 (Metraipolis archive dc_fbab9f00fb88, sha256 1378b4febcc157ba7c59f711ad832386b8985bb679e4a95b8bfbd57159434e26)
BibTeX
@misc{dcfbab9f00fb88,
  title = {From World Models to World Action Models: Rethinking Next-State Prediction — arXiv:2609.34414},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34414},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fbab9f00fb88; sha256 1378b4febcc157ba7c59f711ad832386b8985bb679e4a95b8bfbd57159434e26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve into World-Action Models (WAMs), existing methods still fix the next state before training as RGB, a single latent feature, or a static combination of predefined targets, thereby constraining action learning to the inductive biases preserved by a particular representation. To address this limitation, we propose CF-WAM, a dynamic next-state prediction framework that samples visual, semantic, geometric, and interaction projections of the same future, standardizes them into a common video form, and supervises a unified WAM across these projections. The action-relevant constraints exposed by these projections accumulate across training steps, forcing WAM to capture the underlying state-transition structure that supports multiple projections of the same action-conditioned future. This dynamic mechanism also provides a natural cross-embodiment dynamics reference frame for Human and Robot learning. By jointly learning across different next-state parameterizations, heterogeneous Human and Robot experience can bypass appearance differences and directly contribute to shared state-transition learning, improving cross-embodiment generalization. Experiments show that CF-WAM improves both training efficiency and final control performance, while translating Human experience effectively into policy gains. CF-WAM achieves state-of-the-art performance on RoboCasa-GR1 with an average success rate of 82.50%, while reaching 82.65% on LIBERO-Plus and up to 84.00% in real-world evaluations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.34414 — 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 2026-10-07T23:52:16.549Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).