Metraipolis › archive › dc_e8932ecf105b

Latent Cluster Analysis for Vision-Language-Action Models — arXiv:2609.02634

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02634
License (as archived)
CC0-1.0
Archived
2026-10-17T05:51:18.741Z
SHA-256 of the archived text
c1303fcadca2192ca6453422e13c21be635e9950cd62ef672422f6eaf1f44e0d
Stable URL of this page
https://metraipolis.com/documento/dc_e8932ecf105b

How to cite

Latent Cluster Analysis for Vision-Language-Action Models — arXiv:2609.02634 — arXiv (en), https://arxiv.org/abs/2609.02634 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8932ecf105b (Metraipolis archive dc_e8932ecf105b, sha256 c1303fcadca2192ca6453422e13c21be635e9950cd62ef672422f6eaf1f44e0d)
BibTeX
@misc{dce8932ecf105b,
  title = {Latent Cluster Analysis for Vision-Language-Action Models — arXiv:2609.02634},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02634},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8932ecf105b; sha256 c1303fcadca2192ca6453422e13c21be635e9950cd62ef672422f6eaf1f44e0d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02634. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving their behaviour remain poorly understood. We propose LAVLA, a framework for latent cluster analysis of VLA models, and conduct a layer-wise study of the state-of-the-art GR00T N1.5 model, with particular focus on its action decoder. To better characterise the latent space during action diffusion, we introduce a cross-attention-based embedding-weighting method that amplifies relevant features while suppressing less informative ones. Quantitative evaluation shows that weighted clustering consistently outperforms the baseline. To improve interpretability, we extract human-interpretable concepts for each cluster, linking latent representations to semantic descriptions. Our analysis shows that latent clusters progressively disentangle spatiotemporal and kinematic features, with representations becoming more refined in the middle layers and stabilising toward the output. As such, LAVLA advances the interpretability of language-driven robotic systems.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.02634 — 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 2026-10-17T05:39:02.696Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).