Metraipolis › archive › dc_dce4b79f5f2c

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies — arXiv:2606.15768

Source
arXiv (en)
Original
https://arxiv.org/abs/2606.15768
License (as archived)
CC0-1.0
Archived
2026-11-01T02:43:41.677Z
SHA-256 of the archived text
4cad037d5f30890444e42c85d7ce45c3b236a796be9616f1056f59b08dc2a4f6
Stable URL of this page
https://metraipolis.com/documento/dc_dce4b79f5f2c

How to cite

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies — arXiv:2606.15768 — arXiv (en), https://arxiv.org/abs/2606.15768 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dce4b79f5f2c (Metraipolis archive dc_dce4b79f5f2c, sha256 4cad037d5f30890444e42c85d7ce45c3b236a796be9616f1056f59b08dc2a4f6)
BibTeX
@misc{dcdce4b79f5f2c,
  title = {LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies — arXiv:2606.15768},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2606.15768},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dce4b79f5f2c; sha256 4cad037d5f30890444e42c85d7ce45c3b236a796be9616f1056f59b08dc2a4f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2606.15768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene. World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy. We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM). We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution. LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control. LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference. LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, 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/2606.15768 — 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 2026-11-01T02:16:43.999Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).