Metraipolis › archive › dc_fdbfaed3d7a2

From Pixels to Actions - Towards Native Vision-Language-Action Policies — arXiv:2611.06918

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06918
License (as archived): CC0-1.0
Archived: 2026-11-05T18:30:16.175Z
SHA-256 of the archived text: 3196ccc9c2aa77e091812fd1514706f0435f566aec6b01c75cca192377bd6dd3
Stable URL of this page: https://metraipolis.com/documento/dc_fdbfaed3d7a2

How to cite

From Pixels to Actions - Towards Native Vision-Language-Action Policies — arXiv:2611.06918 — arXiv (en), https://arxiv.org/abs/2611.06918 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdbfaed3d7a2 (Metraipolis archive dc_fdbfaed3d7a2, sha256 3196ccc9c2aa77e091812fd1514706f0435f566aec6b01c75cca192377bd6dd3)

BibTeX

@misc{dcfdbfaed3d7a2,
  title = {From Pixels to Actions - Towards Native Vision-Language-Action Policies — arXiv:2611.06918},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06918},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdbfaed3d7a2; sha256 3196ccc9c2aa77e091812fd1514706f0435f566aec6b01c75cca192377bd6dd3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06918. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action models are typically built on a simple premise: perception is first compressed by visual encoders, and action reasoning begins only afterwards. Yet manipulation often hinges on precisely the visual signals most vulnerable to this abstraction, e.g., local geometry, boundaries, depth, and subtle state changes. This raises a fundamental question: should action policies inherit a fixed visual endpoint, or directly access evolving visual computation? We introduce NEO-VLA, a structurally encoder-free vision-language-action framework. Images are tokenized by lightweight patch convolutional layers and evolve jointly with language throughout the backbone, allowing a flow-matching action expert to draw from instruction-conditioned visual representations at different depths. This simple change reveals a consistent pattern. Native architectures outperform encoder-based counterparts under controlled comparisons; full fine-tuning reduces but does not erase the gap, and additional scale alone cannot recover it. More strikingly, layer-wise probing shows that the action-critical signals often peak well before the final visual representation. Across diverse manipulation settings and distribution shifts, NEO-VLA consequently achieves stronger and more robust control. Together, these results suggest that embodied control benefits from access to visual representations across the computational hierarchy, rather than a fixed encoder output.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.06918 — 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 2026-11-05T18:19:49.068Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).