VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
Overview
This research proposes VLA-Rolling, a framework that reuses action tails from vision-language-action models to enhance control efficiency. By adapting denoising budgets and refining actions through confidence-guided steps, the method achieves faster inference and improved success rates across multiple benchmarks.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · denoising steps: 10 other · Basis not reported
“at this discarded tail retains transferable denoising progress: action-tail initialization can match or outperform a native 10-step Gaussian baseline using fewer denoising steps. However, the optimal denoising budget varies substantially across samples, indicating that tail reuse should be adapted to the updated environment. Based on this observation, we introduce VLA-Rolling, a lightweight inference framework that r”
Exact source · revision 4Source owner not reported
Reported quantity · model--benchmark pairs: 16 other · Basis not reported
“euses action tails through three stages: action-tail inheritance, per-action confidence estimation, and confidence-guided refinement through renoising and denoising budget allocation, while the underlying VLA remains frozen. Across $\pi_{0.5}$, SmolVLA, X-VLA, and MolmoAct2 on LIBERO, MetaWorld, LIBERO-Plus, and RoboTwin 2.0, VLA-Rolling reduces action-chunk inference cost in all 16 model--benchmark pairs, achieving”
Exact source · revision 4Source owner not reported
Evidence dependency changes (3)
- 2026-10-30T22:17:31.277Z · evidence updated · source revision 4. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T22:17:14.405Z · evidence updated · source revision 4. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-22T12:55:29.860Z · evidence updated · source revision 4. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalVLA-Roll, Fewer Denoising Steps, Better Control via Adaptive Action Reuse
This research proposes VLA-Rolling, a framework that reuses action tails from vision-language-action models to enhance control efficiency. By adapting denoising budgets and refining actions through confidence-guided steps, the method achieves faster inference and improved success rates across multiple benchmarks.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).