VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models
VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models
VLA-ACL is a novel approach that prunes visual tokens in vision-language-action models using action-level supervision, while keeping the base model frozen. It achieves up to 87.5% token pruning, 75% computation reduction, and a 1.5x inference speedup on LIBERO and real-world tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
inference speedup
1.5
- code: Available Artifact link Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
s to remain consistent with the full-context teacher, with ground-truth actions as auxiliary supervision. This directly ties token selection to its effect on the downstream control output. Experiments on LIBERO and real-world manipulation tasks show that VLA-ACL prunes up to 87.5% of visual tokens while retaining competitive performance, reduces computation by up to 75%, and achieves a 1.5x inference speedup. These r
Open source S4
esults establish a stronger performance-efficiency trade-off than existing frozen-VLA pruning methods and demonstrate the value of action-level supervision for visual token selection. Code is available at https://github.com/du-owen/VLA-ACL.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org