Metraipolis › archive › dc_bc7cc81f5e85

PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies — arXiv:2610.12285

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12285
License (as archived)
CC0-1.0
Archived
2026-10-09T06:35:31.544Z
SHA-256 of the archived text
0516d21e003df9d53ca6b3ae7ba2c0cde3f19bb3f6f12e8c34ab98e89272f98c
Stable URL of this page
https://metraipolis.com/documento/dc_bc7cc81f5e85

How to cite

PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies — arXiv:2610.12285 — arXiv (en), https://arxiv.org/abs/2610.12285 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc7cc81f5e85 (Metraipolis archive dc_bc7cc81f5e85, sha256 0516d21e003df9d53ca6b3ae7ba2c0cde3f19bb3f6f12e8c34ab98e89272f98c)
BibTeX
@misc{dcbc7cc81f5e85,
  title = {PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies — arXiv:2610.12285},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12285},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc7cc81f5e85; sha256 0516d21e003df9d53ca6b3ae7ba2c0cde3f19bb3f6f12e8c34ab98e89272f98c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12285. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future representation is modeled and how it conditions action generation. We introduce PLaW-VLA, which models task-relevant future states in a pretrained prediction-oriented representation space, reducing the need to predict control-irrelevant visual details. Built on a Mixture-of-Transformers architecture, PLaW-VLA conditions action generation on observation history, current task semantics, and predicted future states through structured causal attention. Experiments show a +11.8 percentage-point (pp) gain over reactive policies on RoboTwin Hard Horizon III and a +1.77 pp gain over reconstruction-oriented latent prediction on zero-shot LIBERO-Plus, supporting improved long-horizon control and generalization under distribution shift, respectively. By avoiding low-level visual reconstruction, PLaW-VLA lowers the burden of future prediction, enabling a lightweight latent world model with parallel future prediction and about 1/19 the inference latency of generative world-action modeling at comparable policy performance.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.12285 — 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 2026-10-09T05:55:22.295Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).