SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
Overview
This research presents SpecPrune-VLA, a training-free two-level pruning method for Vision-Language-Action (VLA) models. The approach leverages spatial-temporal consistency in VLA tasks by combining local information with global context to reduce visual tokens. It features action-level static pruning using global history and local attention, layer-level dynamic pruning based on importance, and a lightweight action-aware controller that adjusts pruning aggressiveness according to end-effector speed. Experiments demonstrate up to 1.57x speedup in LIBERO simulation and 1.70x on real-world tasks with negligible impact on success rates.
Generated from attributed reports · Updated 2 hours ago
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 · speedup factor: 1.57 other · Basis not reported · Differing source assertions
“chieves up to 1.57$\times$ speedup in LIBERO simulation and 1.70$\times$ on real-world tasks, with negligible success rate degradation.”
Exact source · revision 1Source owner not reported
Reported quantity · speedup factor: 1.7 other · Basis not reported · Differing source assertions
“chieves up to 1.57$\times$ speedup in LIBERO simulation and 1.70$\times$ on real-world tasks, with negligible success rate degradation.”
Exact source · revision 1Source owner not reported
Reported quantity · Reported success rate: 20 percent · Basis not reported
“arXiv:2509.05614v4 Announce Type: replace-cross Abstract: Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration methods focus on local information from the current action step and ignore the global context, leading to >20% success rate d”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalSpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
This research presents SpecPrune-VLA, a training-free two-level pruning method for Vision-Language-Action (VLA) models. The approach leverages spatial-temporal consistency in VLA tasks by combining local information with global context to reduce visual tokens. It features action-level static pruning using global history and local attention, layer-level dynamic pruning based on importance, and a lightweight action-aware controller that adjusts pruning aggressiveness according to end-effector speed. Experiments demonstrate up to 1.57x speedup in LIBERO simulation and 1.70x on real-world tasks with negligible impact on success rates.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).