T3R: Training-Free Two-Stage Token Refinement Towards Efficient and Robust VLA Models
Overview
This paper introduces T3R, a training-free two-stage token refinement framework designed to enhance the efficiency and robustness of Vision-Language-Action (VLA) models.
Generated from attributed reports · Updated 2 days 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 · milliseconds per inference call attributed to pruning and attention bias: 7.8 other · Basis not reported
“matching the unpruned success rate, and improves success by up to 7 percentage points under out-of-distribution object-placement perturbations. The timing comparison attributes 7.8 ms per inference call to pruning and attention-bias application. As input resolution increases, LLM-forward profiling shows up to a 3.3x speedup over the unpruned baseline. Evaluations across LIBERO, SIMPLER, and RoboTwin with three VLA ba”
Exact source · revision 1Source owner not reported
Reported quantity · speedup factor over unpruned baseline: 3.3 other · Basis not reported
“matching the unpruned success rate, and improves success by up to 7 percentage points under out-of-distribution object-placement perturbations. The timing comparison attributes 7.8 ms per inference call to pruning and attention-bias application. As input resolution increases, LLM-forward profiling shows up to a 3.3x speedup over the unpruned baseline. Evaluations across LIBERO, SIMPLER, and RoboTwin with three VLA ba”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalT3R: Training-Free Two-Stage Token Refinement Towards Efficient and Robust VLA Models
This paper introduces T3R, a training-free two-stage token refinement framework designed to enhance the efficiency and robustness of Vision-Language-Action (VLA) models.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).