Metraipolis › archive › dc_f525fdfe74ee

SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations — arXiv:2609.39873

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39873
License (as archived)
CC0-1.0
Archived
2026-10-07T15:12:15.870Z
SHA-256 of the archived text
e85f9f6476b2a0d1ddc30b14dd52003fab058ea4eba3a38324f29b147bce1723
Stable URL of this page
https://metraipolis.com/documento/dc_f525fdfe74ee

How to cite

SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations — arXiv:2609.39873 — arXiv (en), https://arxiv.org/abs/2609.39873 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f525fdfe74ee (Metraipolis archive dc_f525fdfe74ee, sha256 e85f9f6476b2a0d1ddc30b14dd52003fab058ea4eba3a38324f29b147bce1723)
BibTeX
@misc{dcf525fdfe74ee,
  title = {SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations — arXiv:2609.39873},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39873},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f525fdfe74ee; sha256 e85f9f6476b2a0d1ddc30b14dd52003fab058ea4eba3a38324f29b147bce1723},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39873. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

World action models (WAMs) are large embodied policies that jointly predict future video and the actions to execute, emitting a fixed-length action chunk per inference call. Such a policy allocates its computational budget uniformly in time, unable to execute for longer over free-space motion or to spend more inference on contact-rich manipulation, which limits the throughput a WAM can reach when served in the cloud. We present SplineWAM, which adaptively compresses the action trajectory into a fixed-size window of cubic B-spline parameters, fitting the knot times to the characteristics of the motion. One parameter budget then decodes into chunks of varying temporal resolution and duration, and both the executed span and the interval until the next policy call follow from the prediction itself. Aligning the video supervision to the fitted knot times of the demonstration rather than to a uniform grid concentrates the supervised frames where the action trajectory is complex. For asynchronous deployment we introduce Jacobian-Pullback Real-Time Chunking (JP-RTC), which imposes chunk continuity on the decoded raw actions the robot executes rather than on the spline parameters, and corrects the parameters through the decoder so that the executed prefix agrees with the actions already committed. On LIBERO-Plus and RoboCasa, SplineWAM improves success rate over an action chunking WAM by $8.2$ and $4.4$ points while cutting policy calls per episode by 22% and 26%. On three bimanual real-robot tasks under asynchronous execution, it leads or matches the baseline while decoding 1.2 to 1.6 times as much executed motion per call.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.39873 — 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 2026-10-07T14:44:47.479Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).