Metraipolis › archive › dc_2c8b09421a13
Retrieve in Time, Correct in Frequency — arXiv:2608.04527
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04527
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:50:01.661Z
- SHA-256 of the archived text
5df6a696e7fb731c7470a58f6999855de31588e6951622c4703a348354723d55- Stable URL of this page
https://metraipolis.com/documento/dc_2c8b09421a13
How to cite
Retrieve in Time, Correct in Frequency — arXiv:2608.04527 — arXiv (en), https://arxiv.org/abs/2608.04527 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c8b09421a13 (Metraipolis archive dc_2c8b09421a13, sha256 5df6a696e7fb731c7470a58f6999855de31588e6951622c4703a348354723d55)
BibTeX
@misc{dc2c8b09421a13,
title = {Retrieve in Time, Correct in Frequency — arXiv:2608.04527},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04527},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c8b09421a13; sha256 5df6a696e7fb731c7470a58f6999855de31588e6951622c4703a348354723d55},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04527. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Frozen vision-language-action (VLA) policies generate temporally extended action chunks, but long-horizon manipulation remains vulnerable to accumulated execution error and visual aliasing across task stages. Successful rollouts provide useful corrective evidence, yet current frame retrieval can return progress-misaligned actions,while direct replay or time-domain fusion can overwrite the reactive structure of the policy proposal. We introduce Retrieve in Time, Correct in Frequency (RTCF), a training-free test-time correction framework that improves frozen VLA performance with low model-side this http URL separates which experience to retrieve from which part of its action to transfer. Progressive Memory Alignment (PMA) causally aligns the growing visual execution history with complete successful trajectories through incrementally updated monotonic frontiers, jointly identifying a relevant memory and the current aligned memory position without stage labels. From the aligned action chunk,RTCF transfers a coefficient-wise-clipped low-frequency residual on motion channels. Higher-frequency components and gripper decisions remain inherited from the frozen policy. Across four LIBERO suites and 2,000 episodes per condition, RTCF raises aggregate success from 86.4% to 88.4% and improves LIBERO-Long from 61.6% to 68.6%.These gains require no parameter updates, repeated VLA inference, or additional GPU resources: correction can be performed on the client CPU after a single policy invocation, and the median latencies sum to only 10.99 ms per action chunk Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.04527 — 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 2026-10-31T11:39:29.937Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).