Metraipolis › archive › dc_33085aabe3f3

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models — arXiv:2609.03681

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03681
License (as archived)
CC0-1.0
Archived
2026-10-17T02:57:30.174Z
SHA-256 of the archived text
4b77f18110d58f477bf5ca9f1a2756c49543027561f0eaa47560ca552c9d6b09
Stable URL of this page
https://metraipolis.com/documento/dc_33085aabe3f3

How to cite

WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models — arXiv:2609.03681 — arXiv (en), https://arxiv.org/abs/2609.03681 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33085aabe3f3 (Metraipolis archive dc_33085aabe3f3, sha256 4b77f18110d58f477bf5ca9f1a2756c49543027561f0eaa47560ca552c9d6b09)
BibTeX
@misc{dc33085aabe3f3,
  title = {WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models — arXiv:2609.03681},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03681},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33085aabe3f3; sha256 4b77f18110d58f477bf5ca9f1a2756c49543027561f0eaa47560ca552c9d6b09},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03681. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Post-training VLA policies typically rely on supervised fine-tuning with costly expert demonstrations or reinforcement learning with expensive and potentially unstable real-world exploration. World models offer a promising alternative by evaluating candidate behaviors through imagined futures, yet effective post-training requires more than accurate prediction: imagination must be scheduled where it is useful, bounded within reliable horizons, and translated into trustworthy policy supervision. In robotic manipulation, the value of imagination varies substantially across execution stages, while extended rollouts can accumulate prediction errors and introduce unreliable learning signals. We introduce WISE (World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models), a unified framework that coordinates when and how world-model imagination is used during policy refinement. WISE selectively invokes imagination at interaction-relevant states, performs bounded multi-view rollouts, evaluates candidate futures using progress and completion signals, and uses their relative outcomes to refine actions generated from real interaction contexts. Extensive experiments with both $\pi_0$ and $\pi_{0.5}$ demonstrate consistent improvements across diverse manipulation tasks while reducing GPU computation time by approximately 80% compared with full imagination. Real-world evaluations further show substantial gains in robustness and generalization under diverse real-world distribution shifts.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-04 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.03681 — 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 2026-10-17T02:33:25.394Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).