Metraipolis › archive › dc_0d5cb7bd8bb6
TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies — arXiv:2610.09451
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09451
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:49:03.160Z
- SHA-256 of the archived text
f6983386e654d730f52138c7f403363a93877eb483e253973d16d11cb68ebdf8- Stable URL of this page
https://metraipolis.com/documento/dc_0d5cb7bd8bb6
How to cite
TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies — arXiv:2610.09451 — arXiv (en), https://arxiv.org/abs/2610.09451 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d5cb7bd8bb6 (Metraipolis archive dc_0d5cb7bd8bb6, sha256 f6983386e654d730f52138c7f403363a93877eb483e253973d16d11cb68ebdf8)
BibTeX
@misc{dc0d5cb7bd8bb6,
title = {TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies — arXiv:2610.09451},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09451},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d5cb7bd8bb6; sha256 f6983386e654d730f52138c7f403363a93877eb483e253973d16d11cb68ebdf8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09451. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action (VLA) models are effective at understanding what task to perform, but provide limited control over how it should be executed, such as moving quickly or slowly. We introduce TempoBridge, a lightweight framework that uses frozen VLA representations to modulate actions according to tempo cues in the instruction at each task phase, without additional tempo-conditioned robot demonstrations or tempo-specific base-policy fine-tuning. TempoBridge extracts tempo cues from contextual VLM representations, aligns them with task progress through a causal phase router, and modulates nominal motion commands during execution. Across LIBERO tasks, TempoBridge improves Tempo Success Rate from 52.6% to 89.7% under canonical tempo instructions while retaining high task success. It also preserves near-baseline performance when no tempo cue is present and generalizes to unseen tempo expressions without additional training. Experiments on a physical robot further demonstrate language-conditioned tempo modulation in real-world manipulation. 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/2610.09451 — 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 2026-10-08T12:18:30.526Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).