Zuxuan Wu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust, and reliable real-world agents.
VLA-Pro is a plug-and-play framework that enhances cross-task generalization in Vision-Language-Action models by storing and dynamically retrieving task-specific procedural memories, achieving significant improvements in both simulation and real-world robotic manipulation.
Papers
VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
Shengyu Si, Yuanzhuo Lu, Ruimeng Yang, Ziyi Ye +2 more
VLA-Pro is a plug-and-play framework that enhances cross-task generalization in Vision-Language-Action models by storing and dynamically retrieving task-specific procedural memories, achieving signifi…