Preprint
Aug 2026
BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
BridgeVLA++ is developed by equipping BridgeVLA with a unified spatio-temporal memory architecture that models persistent spatial context and temporal interaction history that can reason over observation histories while preserving BridgeVLA's data efficiency and generalization capabilities.
Pei-Yan Li, Yuze Zhu, Yixiang Chen et al.
· 2 citations
· ⚡1