Metraipolis › archive › dc_dc4d8eaa9868
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields — arXiv:2608.08023
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08023
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:12:28.354Z
- SHA-256 of the archived text
a4bb6eac0eeb86c4de2f8cd0a796731787885b4e38b39131bc18eb0eaa4d2ab4- Stable URL of this page
https://metraipolis.com/documento/dc_dc4d8eaa9868
How to cite
4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields — arXiv:2608.08023 — arXiv (en), https://arxiv.org/abs/2608.08023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc4d8eaa9868 (Metraipolis archive dc_dc4d8eaa9868, sha256 a4bb6eac0eeb86c4de2f8cd0a796731787885b4e38b39131bc18eb0eaa4d2ab4)
BibTeX
@misc{dcdc4d8eaa9868,
title = {4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields — arXiv:2608.08023},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08023},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc4d8eaa9868; sha256 a4bb6eac0eeb86c4de2f8cd0a796731787885b4e38b39131bc18eb0eaa4d2ab4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Building on recent advances in world models, World Action Models (WAMs) jointly model video prediction and action generation. However, they typically represent videos in 2D pixel space, creating a representation gap with 3D space in which robotic actions are executed. Recent 3D approaches introduce 3D information, but fail to fully exploit the dynamics of 3D structures. In this work, we propose 4D-WAM, a model-agnostic training strategy that injects spatiotemporal knowledge from 3D trajectory fields into WAMs through representation alignment. To this end, we introduce two complementary objectives: 1) motion alignment, which aligns temporal feature variations across adjacent frames and encourages the model to build local 4D awareness during training, and 2) destination alignment, which guides the model to infer the final destination from the source frame by minimizing the gap between their attention-like similarity distributions. Together, these objectives provide both local motion supervision and long-horizon goal guidance, enabling WAMs to learn trajectory-level spatiotemporal representations. Extensive in-distribution and out-of-distribution experiments across different base models demonstrate the model's improvements in spatial understanding, execution precision, robustness, generalization, and versatility. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.08023 — 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 2026-10-19T09:11:58.732Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).