Metraipolis › archive › dc_59cd98ecf8f4

PAIR: Bridging Perception and Action in Vision-Language-Action Models — arXiv:2610.09016

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.09016
License (as archived): CC0-1.0
Archived: 2026-10-08T11:06:49.991Z
SHA-256 of the archived text: 50895be80b38faeb27d3bfcd8dbc15b92b433db4f9904674cef3b0ae4c87b9c6
Stable URL of this page: https://metraipolis.com/documento/dc_59cd98ecf8f4

How to cite

PAIR: Bridging Perception and Action in Vision-Language-Action Models — arXiv:2610.09016 — arXiv (en), https://arxiv.org/abs/2610.09016 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_59cd98ecf8f4 (Metraipolis archive dc_59cd98ecf8f4, sha256 50895be80b38faeb27d3bfcd8dbc15b92b433db4f9904674cef3b0ae4c87b9c6)

BibTeX

@misc{dc59cd98ecf8f4,
  title = {PAIR: Bridging Perception and Action in Vision-Language-Action Models — arXiv:2610.09016},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09016},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_59cd98ecf8f4; sha256 50895be80b38faeb27d3bfcd8dbc15b92b433db4f9904674cef3b0ae4c87b9c6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09016. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models map visual observations and language instructions to continuous robot actions. This task requires a transition from representations that describe the scene and instruction to representations that support action generation. Many continuous-action VLAs leave this transition implicit and supervise it mainly through the final action-prediction loss. We introduce PAIR, a framework that learns a shared perception-action representation between these two spaces. During training, a Masked Action Autoencoder encodes expert action chunks into horizon-aligned Action Latent Tokens. A Bridge Module extracts task-relevant features from the current visual-language representations. PAIR aligns these features with the Action Latent Tokens to form Bridge Tokens that preserve task information and capture the structure of expert actions. The Bridge Tokens are then projected into the action-token space and injected into the initial Action Tokens, providing an action-ready starting point for Action Expert refinement. At inference, the autoencoder is removed, and the Bridge Tokens are generated only from the current observation and instruction. Experiments on LIBERO, LIBERO-Plus, and CALVIN ABC-D show gains for the evaluated OpenVLA-OFT and VLA-Adapter models. On LIBERO-Plus, PAIR raises VLA-Adapter's success rate from 59.1% to 64.2%. On CALVIN, it increases VLA-Adapter's average completed sequence length from 4.42 to 4.53. Across seven real-world tasks, PAIR raises OpenVLA-OFT's success rate from 51.4% to 65.0%. Representation analyses show that Bridge Tokens retain task information while making continuous-action information accessible before Action Expert refinement. These results support a shared intermediate representation as a useful interface between perception and action in continuous-action VLAs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.09016 — 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 2026-10-08T10:14:05.891Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).