Metraipolis › archive › dc_33dedc9cb4f4

PRISM: Primitive Routing via In-context Skill Mixing for Retentive VLA Adaptation — arXiv:2611.08917

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08917
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:57.202Z
SHA-256 of the archived text
2cbe136c9247cc4b1e296def87f1b7128150f57a0ff0af427e2c6c69be1e9870
Stable URL of this page
https://metraipolis.com/documento/dc_33dedc9cb4f4

How to cite

PRISM: Primitive Routing via In-context Skill Mixing for Retentive VLA Adaptation — arXiv:2611.08917 — arXiv (en), https://arxiv.org/abs/2611.08917 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33dedc9cb4f4 (Metraipolis archive dc_33dedc9cb4f4, sha256 2cbe136c9247cc4b1e296def87f1b7128150f57a0ff0af427e2c6c69be1e9870)
BibTeX
@misc{dc33dedc9cb4f4,
  title = {PRISM: Primitive Routing via In-context Skill Mixing for Retentive VLA Adaptation — arXiv:2611.08917},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08917},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33dedc9cb4f4; sha256 2cbe136c9247cc4b1e296def87f1b7128150f57a0ff0af427e2c6c69be1e9870},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08917. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models promise a single language-conditioned policy adaptable to many manipulation behaviors, yet deployment additionally requires skill retention and long-horizon composition: a policy must retain previously acquired skills and reuse them inside composite tasks whose behavior changes across phases. The standard recipe absorbs every new task into one shared update, which provides neither a parameter-level locus for reusable skills nor a mechanism for invoking each skill along the trajectory. We observe that this missing structure is latent rather than absent: per-skill low-rank updates of a pretrained VLA occupy a robustly distinguishable, low-dimensional subspace, and a single composite-task LoRA concentrates roughly half of its Frobenius energy in this subspace, against a near-zero matched random-rotation control. Building on this geometry, we introduce PRISM, which represents reusable skills as parameter-level primitives: each skill family is stored as a dedicated low-rank action-expert adapter in a primitive bank, primitives are augmented with skill-specific low-rank residuals and composed at inference by a per-chunk VLM-conditioned router that reads the prefix representation to track task progress, and the router is supervised by per-chunk labels from a deterministic, task-conditioned, action-derived oracle. During composite training, the vision encoder, the language LoRA, the skill residuals, the router, and the shared action projections and time MLP are updated; every primitive is held frozen, so the base per-skill action-expert adapters are preserved by construction. On RoboCasa365, PRISM achieves 56.43% atomic-skill success and reaches 20.00% on long-horizon composite tasks, while a standard $\pi_{0.5}$-LoRA two-stage fine-tune reaches 17.86% atomic and 17.50% composite success. We additionally validate PRISM on an AgileX PIPER real-robot setup.

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/2611.08917 — 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 2026-11-09T22:38:02.171Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).