SOURCE-LINKED INTELLIGENCE

VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, numerical format, and calibration. We introduce \textbf{VLAQuantBench}, a controlled evaluation with 409 runs and 94,574 simulation episodes: four models on LIBERO, with X-VLA additionally evaluated on three simulation benchmark families. Under uncalibrated W4A4 round-to-nearest quantization, expanding a $π_{0.5}$ action-head subset from 126 to 167 layers raises success from 7.0\% to 70.5\%. Fixed-observation replay con

Read original source ↗ Open in workspace

recordType

paper

region

Global