Metraipolis › archive › dc_a85bfdc0950d

ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models — arXiv:2610.08150

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08150
License (as archived)
CC0-1.0
Archived
2026-10-07T13:12:17.578Z
SHA-256 of the archived text
6ceef91703b98d96034dff1e5e331e62585957547a3d0af6b8056e547602b816
Stable URL of this page
https://metraipolis.com/documento/dc_a85bfdc0950d

How to cite

ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models — arXiv:2610.08150 — arXiv (en), https://arxiv.org/abs/2610.08150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a85bfdc0950d (Metraipolis archive dc_a85bfdc0950d, sha256 6ceef91703b98d96034dff1e5e331e62585957547a3d0af6b8056e547602b816)
BibTeX
@misc{dca85bfdc0950d,
  title = {ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models — arXiv:2610.08150},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08150},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a85bfdc0950d; sha256 6ceef91703b98d96034dff1e5e331e62585957547a3d0af6b8056e547602b816},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models have become a central paradigm for robot policy learning, which predict actions in three forms: raw action chunks, discrete action tokens, or continuous action latents. However, existing action representations primarily model action trajectories, with limited consideration of the visual dynamics induced by these actions. We introduce ViDAL, a Visual Dynamics-grounded Action Latent Space that anchors continuous action latents in the future visual dynamics of the scene. Specifically, ViDAL learns action latent space by training an Action Variational Autoencoder (Action VAE) to reconstruct action chunks while aligning its latent with future scene dynamics. When integrated into downstream robot policies, the proposed Action VAE serves as a plug-in action interface compatible with multiple VLA architectures and enables optional future-video prediction as an additional capability. Empirically, ViDAL outperforms competitive baselines on LIBERO with 98.1% average success, improves a multi-task $\pi_{0.5}$ policy on RoboTwin 2.0 from 54.3% to 65.5% (Clean) and from 33.2% to 43.1% (Random) success rates over 50 dual-arm tasks, and yields 20.0% and 23.4% absolute success-rate gains on real-world single-arm Franka and dual-arm ARX robot platforms.

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/2610.08150 — 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 2026-10-07T12:42:33.606Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).