Metraipolis › archive › dc_08502cf60ff2

Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actions — arXiv:2608.03563

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03563
License (as archived): CC0-1.0
Archived: 2026-10-31T13:08:25.724Z
SHA-256 of the archived text: adfead35bee686547620d755c8cf4b752de4918e33c207f947d495c31af05023
Stable URL of this page: https://metraipolis.com/documento/dc_08502cf60ff2

How to cite

Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actions — arXiv:2608.03563 — arXiv (en), https://arxiv.org/abs/2608.03563 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08502cf60ff2 (Metraipolis archive dc_08502cf60ff2, sha256 adfead35bee686547620d755c8cf4b752de4918e33c207f947d495c31af05023)

BibTeX

@misc{dc08502cf60ff2,
  title = {Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actions — arXiv:2608.03563},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03563},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08502cf60ff2; sha256 adfead35bee686547620d755c8cf4b752de4918e33c207f947d495c31af05023},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03563. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

VLA models are trained to predict robot actions from visual and language observations. This is a natural choice, but it creates a mismatch: VLMs encode rich, high-level representations of scenes and goals, while robot actions are low-level signals with limited task structure. We ask whether changing what the policy is trained to predict, rather than how it is architecturally designed, can yield better and more efficiently trained policies. We propose UVT (Unified Visuomotor Target), a unified latent prediction target that jointly encodes motor control and visual scene transition information, requiring no architectural changes and no additional data. Applied to two representative VLA systems across simulation benchmarks and real bimanual manipulation tasks, UVT improves training efficiency, final task performance, and policy robustness, with particularly strong gains under limited training budgets and challenging environmental conditions. Rollout videos and additional qualitative results are available at our project webpage: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.03563 — 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 2026-10-31T12:55:56.561Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).