Metraipolis › archive › dc_03cd83f4fd7d

STAR: Steering Action Representations during Inference — arXiv:2610.41009

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41009
License (as archived)
CC0-1.0
Archived
2026-11-02T07:30:49.801Z
SHA-256 of the archived text
51941793e011ef4205a28025ec52b9ddb213daa061f45dfebc2af53b4245a6c9
Stable URL of this page
https://metraipolis.com/documento/dc_03cd83f4fd7d

How to cite

STAR: Steering Action Representations during Inference — arXiv:2610.41009 — arXiv (en), https://arxiv.org/abs/2610.41009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_03cd83f4fd7d (Metraipolis archive dc_03cd83f4fd7d, sha256 51941793e011ef4205a28025ec52b9ddb213daa061f45dfebc2af53b4245a6c9)
BibTeX
@misc{dc03cd83f4fd7d,
  title = {STAR: Steering Action Representations during Inference — arXiv:2610.41009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_03cd83f4fd7d; sha256 51941793e011ef4205a28025ec52b9ddb213daa061f45dfebc2af53b4245a6c9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action models (VLAs) map language instructions and visual observations to robot actions, showing strong capabilities across robotic manipulation tasks. However, in our probing experiment, we find that action representations near the action output do not fully preserve task-relevant visual grounding. Motivated by this late-layer grounding gap, we introduce STAR, for STeering Action Representations, a training-free inference method for pre-trained VLAs. STAR applies an exponential moving average over late-layer residual updates, allowing later action representations to inherit object-aware update directions from earlier layers without model updates or architectural changes. It further uses recent proprioceptive states to adapt the mixing strength, using conservative mixing when execution dynamics change rapidly. Experiments on robot manipulation benchmarks show that STAR improves late-layer object awareness and increases average task success rates by 4.0 percentage points. Our code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41009 — 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 2026-11-02T07:26:57.771Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).