Metraipolis › archive › dc_082a3bf05e9f

SMILE: Smooth Motion for Improved Long-Horizon VLA Execution — arXiv:2608.29432

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29432
License (as archived)
CC0-1.0
Archived
2026-10-17T10:06:46.719Z
SHA-256 of the archived text
f186f12cd40eb57c26a8cc9a7282e9bd50360a49128b01f50558d0b306d56a86
Stable URL of this page
https://metraipolis.com/documento/dc_082a3bf05e9f

How to cite

SMILE: Smooth Motion for Improved Long-Horizon VLA Execution — arXiv:2608.29432 — arXiv (en), https://arxiv.org/abs/2608.29432 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_082a3bf05e9f (Metraipolis archive dc_082a3bf05e9f, sha256 f186f12cd40eb57c26a8cc9a7282e9bd50360a49128b01f50558d0b306d56a86)
BibTeX
@misc{dc082a3bf05e9f,
  title = {SMILE: Smooth Motion for Improved Long-Horizon VLA Execution — arXiv:2608.29432},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29432},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_082a3bf05e9f; sha256 f186f12cd40eb57c26a8cc9a7282e9bd50360a49128b01f50558d0b306d56a86},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29432. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models reduce inference cost by executing multiple actions per call, but longer horizons often degrade accuracy because raw chunks contain jitter and outliers. We introduce SMILE, an architecture-preserving interface that predicts B-spline coefficients and decodes them into smooth action sequences. SMILE changes only the action representation, enabling longer fixed horizons while retaining each baseline's backbone and model scale. We apply SMILE to SmolVLA, Evo1, VPP, and DAWN, improving accuracy and amortized inference efficiency across LIBERO, CALVIN, and real-world experiments. SMILE-Evo1 reaches 98.0% with a 1.1x speedup on LIBERO, while SMILE-VPP reaches an average length of 4.42 with a 1.5x speedup on CALVIN. At a matched execution horizon of 10, SMILE-SmolVLA reduces non-boundary acceleration by 78.6% and velocity sign-change rate by 42.3%. Real-world xArm tests show higher success, fewer drops, and fewer contacts. These results establish smooth coefficient-space generation as a route to accurate, efficient long-horizon VLA execution. Project page: this http URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.29432 — 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 2026-10-17T09:58:57.775Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).