Metraipolis › archive › dc_2e37c32e804b

FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models — arXiv:2609.19475

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19475
License (as archived)
CC0-1.0
Archived
2026-10-10T05:25:24.686Z
SHA-256 of the archived text
a6640b5760e37f77d1da5fe8bb7407d1993bc2b1d530d248216a582a152212a1
Stable URL of this page
https://metraipolis.com/documento/dc_2e37c32e804b

How to cite

FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models — arXiv:2609.19475 — arXiv (en), https://arxiv.org/abs/2609.19475 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e37c32e804b (Metraipolis archive dc_2e37c32e804b, sha256 a6640b5760e37f77d1da5fe8bb7407d1993bc2b1d530d248216a582a152212a1)
BibTeX
@misc{dc2e37c32e804b,
  title = {FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models — arXiv:2609.19475},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19475},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e37c32e804b; sha256 a6640b5760e37f77d1da5fe8bb7407d1993bc2b1d530d248216a582a152212a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19475. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion-based Vision-Language-Action (VLA) models achieve strong performance in embodied tasks, but their iterative sampling imposes heavy computational and memory-access cost, blocking real-time deployment on edge platforms. Existing acceleration methods either require expensive training (e.g., distillation, flow matching) or degrade perception via statically scheduled pruning and caching, ignoring the dynamic workload variance of robotic interactions. This paper presents FASA (Feedback-Aware Sampling Adaptation), a training-free runtime framework that treats real-time multimodal feedback as a control signal for the denoising pipeline: an interaction-driven range adaptor modulates the global sampling-step budget based on visual and gripper-force feedback, and a proprioception-aware step adaptor pinpoints the optimized step within the adapted range. This co-designed framework allows the underlying hardware architecture to adaptively match the workload demands of different execution phases. Comparative evaluations across several benchmarks show that the inference speed can be increased by up to 1.45$\times$ while maintaining competitive success rates, providing a novel dynamic runtime architecture paradigm for deploying heavy generative embodied AI workloads onto resource-constrained computing platforms.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.19475 — 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 2026-10-10T04:47:38.823Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).