Metraipolis › archive › dc_e08cb28928cb

SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces — arXiv:2610.19651

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19651
License (as archived)
CC0-1.0
Archived
2026-10-15T21:56:22.895Z
SHA-256 of the archived text
a6ab04edd2bccca96493d1a60a0721688dc2324bed6405815499ded5bd869282
Stable URL of this page
https://metraipolis.com/documento/dc_e08cb28928cb

How to cite

SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces — arXiv:2610.19651 — arXiv (en), https://arxiv.org/abs/2610.19651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e08cb28928cb (Metraipolis archive dc_e08cb28928cb, sha256 a6ab04edd2bccca96493d1a60a0721688dc2324bed6405815499ded5bd869282)
BibTeX
@misc{dce08cb28928cb,
  title = {SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces — arXiv:2610.19651},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e08cb28928cb; sha256 a6ab04edd2bccca96493d1a60a0721688dc2324bed6405815499ded5bd869282},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Hyperspectral imaging distinguishes RGB-similar objects, but a pretrained vision-language-action model needs a state its frozen decoder can use. SPECTRA-VLA provides a native-width spectral upgrade without retraining the visual encoder or action decoder. A learned continuous residual enriches each target token through its own normalized false-color reference; projection, norm control and validation-calibrated injection regulate the change. Across 86 held-out acquisitions, category balanced accuracy rises from 0.812 to 0.883. With identical residuals and scale, own-token addition improves reuse of an external category-derived probe on frozen decoder logits: 0.701 versus 0.590 with pooled replacement, at similar image-disjoint recognition. Five grouped tests covering the same 86 acquisitions recover within-category spectral shape with $R^2=0.802/0.337$ from continuous and posterior-code states. Category-matched spectral swaps further show that own-token composition approximately doubles the target-specific recovery increment after frozen decoding. Spectral enrichment and receiving-token preservation thus work together at the pretrained interface.

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/2610.19651 — 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 2026-10-15T21:38:29.486Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).