AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

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

Wei Li, Renshan Zhang, Rui Shao, Zhijian Fang, Kaiwen Zhou, Zhuotao Tian, Liqiang Nie

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use ID-Pruner on SigLIP and SA-Pruner on DINOv2 instead of ID-Pruner on both (ablation)SD-Pruner · LIBEROoverall success rate (%): 91.9 -> 97.1Improved
use ID-Pruner on SigLIP and SA-Pruner on DINOv2 instead of SA-Pruner on both (ablation)SD-Pruner · LIBEROoverall success rate (%): 94.6 -> 97.1Improved
assign pruners correctly rather than swapped (SA on SigLIP, ID on DINOv2) (ablation)SD-Pruner · LIBEROoverall success rate (%): 95.0 -> 97.1Improved
add HF-Fuser (ablation)SemanticVLA without SA-Coupler · LIBEROoverall success rate (%): 93.6 -> 95.6Improved
add SA-Coupler (ablation)SemanticVLA without HF-Fuser · LIBEROoverall success rate (%): 93.6 -> 94.1Improved
add both HF-Fuser and SA-Coupler (ablation)baseline VLA with pruning · LIBEROoverall success rate (%): 93.6 -> 97.1Improved
raise sparsification ratio from 8x to 16x (ablation)SemanticVLA · LIBEROoverall success rate (%): 97.7 -> 95.8Hurt
raise sparsification ratio from 8x to 32x (ablation)SemanticVLA · LIBEROoverall success rate (%): 97.7 -> 92.0Hurt
lower sparsification ratio from 8x to 4x (ablation)SemanticVLA · LIBEROFLOPs (T): 2.37 T -> 3.28 T with SR unchanged at 97.7Hurt
use instruction-aware pruning instead of FastV at 8x compression (ablation)visual token pruning · LIBEROoverall success rate (%): 88.8 -> 97.7Improved
use instruction-aware pruning instead of SliME at 8x compression (ablation)visual token pruning · LIBEROoverall success rate (%): 85.6 -> 97.7Improved
SemanticVLA vs OpenVLA-OFT on real robotSemanticVLA · Real-world AgileXoverall success rate (%): 55.6% -> 77.8%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy