Metraipolis › archive › dc_896ec4392007

NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields — arXiv:2610.00981

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00981
License (as archived): CC0-1.0
Archived: 2026-10-06T19:16:40.478Z
SHA-256 of the archived text: 016c7bef2981bd1c1e0b43324df8cdf071227c66f71bd07ac3bfe2410f77a366
Stable URL of this page: https://metraipolis.com/documento/dc_896ec4392007

How to cite

NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields — arXiv:2610.00981 — arXiv (en), https://arxiv.org/abs/2610.00981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_896ec4392007 (Metraipolis archive dc_896ec4392007, sha256 016c7bef2981bd1c1e0b43324df8cdf071227c66f71bd07ac3bfe2410f77a366)

BibTeX

@misc{dc896ec4392007,
  title = {NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields — arXiv:2610.00981},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00981},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_896ec4392007; sha256 016c7bef2981bd1c1e0b43324df8cdf071227c66f71bd07ac3bfe2410f77a366},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We focus on language-conditioned flow-based manipulation, where robot flows (robot velocity fields) serve as embodiment-agnostic, motion-centric representations for leveraging data collected from multiple robot platforms. This task is crucial because language-conditioned manipulation is essential for practical robotic systems, yet scaling robot foundation models remains limited by the labor-intensive collection of embodiment-specific data. Existing methods either coarsely approximate robot flows with sparse keypoint displacements, or cannot handle language-conditioned manipulation. To address this limitation, we propose NarrativeFlow, which models robot flows as continuous velocity fields using a flow-matching formulation conditioned on language. Accordingly, NarrativeFlow generates robot flows that are physically consistent with real-world manipulation. To validate NarrativeFlow, we have conducted experiments on standard datasets for language-conditioned manipulation. The experimental results show that NarrativeFlow outperforms representative baseline methods on standard evaluation metrics. Furthermore, through real-world experiments, we show that NarrativeFlow achieves higher success rates than baseline methods across multiple manipulation tasks. The project page is available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.00981 — 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 2026-10-06T17:37:36.942Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).