Metraipolis › archive › dc_97bb4cef4935
AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models — arXiv:2608.29208
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29208
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:39:49.209Z
- SHA-256 of the archived text
a6feb4fa9ffda00ce872cce3a1490765f13ce012d88630f2c4e192f370a4ee39- Stable URL of this page
https://metraipolis.com/documento/dc_97bb4cef4935
How to cite
AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models — arXiv:2608.29208 — arXiv (en), https://arxiv.org/abs/2608.29208 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97bb4cef4935 (Metraipolis archive dc_97bb4cef4935, sha256 a6feb4fa9ffda00ce872cce3a1490765f13ce012d88630f2c4e192f370a4ee39)
BibTeX
@misc{dc97bb4cef4935,
title = {AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models — arXiv:2608.29208},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29208},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97bb4cef4935; sha256 a6feb4fa9ffda00ce872cce3a1490765f13ce012d88630f2c4e192f370a4ee39},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29208. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging internet-scale knowledge and multimodal reasoning. However, the intensive computational overhead of VLAs constrains on-device deployment, hindering real-time responses to environmental changes. While various acceleration techniques have been proposed, they often rely on fine-tuning or access to training datasets, which are frequently unavailable due to privacy and proprietary concerns. Moreover, although flow-matching-based VLAs have emerged as efficient alternatives to standard diffusion models, current acceleration efforts largely target VLM inference costs, failing to address the iterative ODE solving process inherent in flow matching inference. To address these limitations, we propose AdaVLA, an online, training-free adaptive framework for fast yet accurate flow-matching-based Vision-Language-Action models. We introduce a novel metric derived from the flow matching trajectory curvature to quantify action generation confidence during inference. This metric enables the dynamic reduction of inference steps and the adaptive adjustment of MLP pruning ratios through an efficiently computed importance evaluation, requiring no access to training data. Experimental results on the LIBERO benchmark using a Jetson AGX Orin device demonstrate that our method achieves $1.87\times$ and $2.24\times$ speedups for $\pi_{0.5}$ and X-VLA, respectively, with negligible degradation in success rates. Furthermore, we validate the robustness of our approach on real-world robotic tasks using SmolVLA.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.29208 — 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 2026-10-17T08:13:26.900Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).