Metraipolis › archive › dc_0f4045aea472

FineCraft: Enhancing VLA Models for Fine-Grained Manipulation — arXiv:2611.03163

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03163
License (as archived)
CC0-1.0
Archived
2026-11-03T18:57:27.053Z
SHA-256 of the archived text
e4bcdea9f9242b0c0ac3ab907066a9278cc16636d947175274a5972fb3722870
Stable URL of this page
https://metraipolis.com/documento/dc_0f4045aea472

How to cite

FineCraft: Enhancing VLA Models for Fine-Grained Manipulation — arXiv:2611.03163 — arXiv (en), https://arxiv.org/abs/2611.03163 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f4045aea472 (Metraipolis archive dc_0f4045aea472, sha256 e4bcdea9f9242b0c0ac3ab907066a9278cc16636d947175274a5972fb3722870)
BibTeX
@misc{dc0f4045aea472,
  title = {FineCraft: Enhancing VLA Models for Fine-Grained Manipulation — arXiv:2611.03163},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03163},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f4045aea472; sha256 e4bcdea9f9242b0c0ac3ab907066a9278cc16636d947175274a5972fb3722870},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03163. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fine-grained manipulation couples instruction grounding, local visual precision, and sustained execution. We present FineCraft, a framework that adapts pretrained models for fine-grained manipulation in the MetaFine Challenge. A task-routed mixture of policies selects independently adapted DINOv2-DiT or pretrained $\pi_{0.5}$ policies through a common observation-action interface. Local visual features help identify the instructed object parts, demonstrations and expert continuations teach the required actions, and new observations guide replanning during execution. FineCraft ranks fourth with an overall score of $0.878$, exceeding the published reference on all five tasks. Official results and local diagnostics characterize performance across visual perturbations, instruction changes, and multi-stage manipulation. Code is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.03163 — 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 2026-11-03T18:17:07.772Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).