Metraipolis › archive › dc_e3471c348ccc
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models — arXiv:2610.00864
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00864
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:11:29.953Z
- SHA-256 of the archived text
adee050bd994c4a14606e276e6f651248f40c0f550b48773581b19883622a979- Stable URL of this page
https://metraipolis.com/documento/dc_e3471c348ccc
How to cite
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models — arXiv:2610.00864 — arXiv (en), https://arxiv.org/abs/2610.00864 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3471c348ccc (Metraipolis archive dc_e3471c348ccc, sha256 adee050bd994c4a14606e276e6f651248f40c0f550b48773581b19883622a979)
BibTeX
@misc{dce3471c348ccc,
title = {Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models — arXiv:2610.00864},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00864},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3471c348ccc; sha256 adee050bd994c4a14606e276e6f651248f40c0f550b48773581b19883622a979},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00864. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. MeanFlow provides a promising framework for this goal, yet its direct application leads to performance collapse. We discover that this stems from two distinctive dynamics exhibited in the RFM velocity field: (1) the ``local acceleration" exhibits stability early on, but surges sharply towards the end of the denoising process, and (2) the spread of its magnitudes across samples widens as denoising progresses. To address these issues, we introduce Kinematic MeanFlow (K-MF), a novel one-step action policy tailored for RFMs. Specifically, grounded in a kinematic identity, K-MF decouples the time derivative term in the MeanFlow formulation into two sub-interval terms separated by an intermediate point. This decoupled formulation enables the two terms to capture early-stage and late-stage denoising dynamics, respectively, while mitigating the error amplification across the process. As a result, our K-MF empowers RFMs to achieve one-step action generation in both training from scratch and fine-tuning paradigms across diverse tasks, while outperforming multi-step flow matching in most settings. In terms of inference efficiency, K-MF reduces action-head latency of GR00T-N1.6 by 67.5%~74.4% across L40 and Jetson Orin in eager and compiled modes, yielding end-to-end latency reductions of 30.3%~54.9%. Code will be available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.00864 — 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 2026-10-06T10:21:28.120Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).