Metraipolis › archive › dc_ee18f3b0897f

BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control — arXiv:2608.13924

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13924
License (as archived)
CC0-1.0
Archived
2026-10-19T04:06:53.209Z
SHA-256 of the archived text
43c5a43cd83728bcc5af1b321adb5562c6ca2b3c63071c3a87e45ea2cf267571
Stable URL of this page
https://metraipolis.com/documento/dc_ee18f3b0897f

How to cite

BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control — arXiv:2608.13924 — arXiv (en), https://arxiv.org/abs/2608.13924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee18f3b0897f (Metraipolis archive dc_ee18f3b0897f, sha256 43c5a43cd83728bcc5af1b321adb5562c6ca2b3c63071c3a87e45ea2cf267571)
BibTeX
@misc{dcee18f3b0897f,
  title = {BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control — arXiv:2608.13924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee18f3b0897f; sha256 43c5a43cd83728bcc5af1b321adb5562c6ca2b3c63071c3a87e45ea2cf267571},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The request-to-handoff gap has three coupled sources: ambiguity about the behavior intended at request time, physical-state drift accumulated during action generation, and residual incompatibility when the new action finally assumes control. BICPO-VLA addresses them in sequence. First, an instruction-aware causal history encoder identifies the behavior supported by the command and current task progress. Second, sequential Haar subspace generation decomposes each action chunk into complementary pairwise scaffold and residual coefficients, enabling two specialized generation stages followed by exact reconstruction. By reducing iterative refinement in the original action space, it shortens the interval over which the robot continues moving before the new chunk becomes available. Finally, BICPO rolls the known outgoing actions to the actual handoff state and applies reference-relative Flow-DPO among behaviorally matched candidates, adapting the generated chunk to the remaining request-to-handoff mismatch without changing its intended behavior.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.13924 — 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 2026-10-19T03:58:09.760Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).