The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
Vision-Language-Action (VLA) models have shown remarkable promise in generalized robotic manipulation. However, their spatial generalization remains fragile. We argue that simply increasing the number of viewpoints is insufficient. Models often fall into the trap of Shortcut Learning, latching onto spurious correlations (e.g., fixed relative poses between objects or between the camera and robot base) rather than learning true spatial relationships. In this work, we propose a data-centric solution to enhance VLA spatial generalization. We utilize a dual-arm setup where one arm performs manipula
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%vlm-starter →
- LinkedLinked via arxiv author · 85%Jincheng Tang →
“The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection”
- LinkedLinked via arxiv author · 85%Yilong Zhu →
“The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection”
- LinkedLinked via arxiv author · 85%Zhengyuan Xie →
“The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection”
- LinkedLinked via arxiv author · 85%Jiang-Jiang Liu →
“The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection”
- LinkedLinked via arxiv author · 85%Jiaxing Zhang →
“The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection”
- PossiblePossibly related (embedding) · 47%sou350121/VLA-Handbook →
- PossiblePossibly related (embedding) · 51%lucidrains/mimic-video →