SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Wei, Zhang, Renshan, Shao, Rui, Fang, Zhijian, Zhou, Kaiwen, Tian, Zhuotao, Nie, Liqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909900699860992
author Li, Wei
Zhang, Renshan
Shao, Rui
Fang, Zhijian
Zhou, Kaiwen
Tian, Zhuotao
Nie, Liqiang
author_facet Li, Wei
Zhang, Renshan
Shao, Rui
Fang, Zhijian
Zhou, Kaiwen
Tian, Zhuotao
Nie, Liqiang
contents Vision-Language-Action (VLA) models have advanced in robotic manipulation, yet practical deployment remains hindered by two key limitations: 1) perceptual redundancy, where irrelevant visual inputs are processed inefficiently, and 2) superficial instruction-vision alignment, which hampers semantic grounding of actions. In this paper, we propose SemanticVLA, a novel VLA framework that performs Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation. Specifically: 1) To sparsify redundant perception while preserving semantic alignment, Semantic-guided Dual Visual Pruner (SD-Pruner) performs: Instruction-driven Pruner (ID-Pruner) extracts global action cues and local semantic anchors in SigLIP; Spatial-aggregation Pruner (SA-Pruner) compacts geometry-rich features into task-adaptive tokens in DINOv2. 2) To exploit sparsified features and integrate semantics with spatial geometry, Semantic-complementary Hierarchical Fuser (SH-Fuser) fuses dense patches and sparse tokens across SigLIP and DINOv2 for coherent representation. 3) To enhance the transformation from perception to action, Semantic-conditioned Action Coupler (SA-Coupler) replaces the conventional observation-to-DoF approach, yielding more efficient and interpretable behavior modeling for manipulation tasks. Extensive experiments on simulation and real-world tasks show that SemanticVLA sets a new SOTA in both performance and efficiency. SemanticVLA surpasses OpenVLA on LIBERO benchmark by 21.1% in success rate, while reducing training cost and inference latency by 3.0-fold and 2.7-fold.SemanticVLA is open-sourced and publicly available at https://github.com/JiuTian-VL/SemanticVLA
format Preprint
id arxiv_https___arxiv_org_abs_2511_10518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
Li, Wei
Zhang, Renshan
Shao, Rui
Fang, Zhijian
Zhou, Kaiwen
Tian, Zhuotao
Nie, Liqiang
Computer Vision and Pattern Recognition
Robotics
Vision-Language-Action (VLA) models have advanced in robotic manipulation, yet practical deployment remains hindered by two key limitations: 1) perceptual redundancy, where irrelevant visual inputs are processed inefficiently, and 2) superficial instruction-vision alignment, which hampers semantic grounding of actions. In this paper, we propose SemanticVLA, a novel VLA framework that performs Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation. Specifically: 1) To sparsify redundant perception while preserving semantic alignment, Semantic-guided Dual Visual Pruner (SD-Pruner) performs: Instruction-driven Pruner (ID-Pruner) extracts global action cues and local semantic anchors in SigLIP; Spatial-aggregation Pruner (SA-Pruner) compacts geometry-rich features into task-adaptive tokens in DINOv2. 2) To exploit sparsified features and integrate semantics with spatial geometry, Semantic-complementary Hierarchical Fuser (SH-Fuser) fuses dense patches and sparse tokens across SigLIP and DINOv2 for coherent representation. 3) To enhance the transformation from perception to action, Semantic-conditioned Action Coupler (SA-Coupler) replaces the conventional observation-to-DoF approach, yielding more efficient and interpretable behavior modeling for manipulation tasks. Extensive experiments on simulation and real-world tasks show that SemanticVLA sets a new SOTA in both performance and efficiency. SemanticVLA surpasses OpenVLA on LIBERO benchmark by 21.1% in success rate, while reducing training cost and inference latency by 3.0-fold and 2.7-fold.SemanticVLA is open-sourced and publicly available at https://github.com/JiuTian-VL/SemanticVLA
title SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2511.10518