Metraipolis › archive › dc_1136cbf17c64

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
2026-11-03T11:44:49.968Z
SHA-256 of the archived text
eed05b921f7d0895daa6f29260ef2dcee740205a6ad1bb231cfc85c572eb2c1e
Stable URL of this page
https://metraipolis.com/documento/dc_1136cbf17c64

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_1136cbf17c64 (Metraipolis archive dc_1136cbf17c64, sha256 eed05b921f7d0895daa6f29260ef2dcee740205a6ad1bb231cfc85c572eb2c1e)
BibTeX
@misc{dc1136cbf17c64,
  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_1136cbf17c64; sha256 eed05b921f7d0895daa6f29260ef2dcee740205a6ad1bb231cfc85c572eb2c1e},
  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 2026-11-03T11:06:52.314Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).