Metraipolis › archive › dc_f0dd357e2771
Looking Back to Move Forward: Temporal Verification for Generative Robot Policies — arXiv:2609.39038
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39038
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T15:11:51.906Z
- SHA-256 of the archived text
95c869464a67493b276e297190e6177e493fcb9643d60628e33fb824cc54490a- Stable URL of this page
https://metraipolis.com/documento/dc_f0dd357e2771
How to cite
Looking Back to Move Forward: Temporal Verification for Generative Robot Policies — arXiv:2609.39038 — arXiv (en), https://arxiv.org/abs/2609.39038 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0dd357e2771 (Metraipolis archive dc_f0dd357e2771, sha256 95c869464a67493b276e297190e6177e493fcb9643d60628e33fb824cc54490a)
BibTeX
@misc{dcf0dd357e2771,
title = {Looking Back to Move Forward: Temporal Verification for Generative Robot Policies — arXiv:2609.39038},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39038},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0dd357e2771; sha256 95c869464a67493b276e297190e6177e493fcb9643d60628e33fb824cc54490a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39038. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative policies have emerged as a promising paradigm for robot learning, combining expressive generative action modeling with scalable imitation learning from large demonstration corpora. However, heterogeneous demonstrations can induce suboptimal action chunks whose errors compound over time, eventually driving the robot into out-of-distribution states from which recovery is difficult. Action verification offers a test-time scaling strategy for mitigating this failure mode by sampling multiple candidate actions and using a verifier to select one for execution. Existing approaches, however, remain temporally myopic and costly to train, evaluating candidates from the current observation alone without accounting for trajectory continuity and often relying on large verifiers and additional expert demonstrations. In this paper, we introduce Temporal Verification (TeV), an efficient temporally aware action verification framework for flow-matching VLAs. TeV first learns a temporal token that summarizes recent observation--action history, enabling candidate chunks to be evaluated as continuations of the execution trajectory rather than as isolated predictions. Conditioned on this token, TeV constructs positive--negative pairs without additional expert demonstrations or preference annotations and trains an energy-based verifier contrastively to assign lower energy to higher-quality, trajectory-consistent action chunks. Beyond post-hoc ranking, TeV further uses the learned energy landscape to guide intermediate flow samples toward lower-energy regions, improving candidates before final selection. Extensive experiments in simulation and real-world settings demonstrate that TeV provides reliably ranks action candidates, improves task success rates, and produces smoother execution trajectories. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.39038 — 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 2026-10-07T14:44:47.408Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).