Jul 2026
Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation
A cache-efficient lifelong Vision-Language-Action learning framework for robotic manipulation, which alleviates the plasticity-stability trade-off with a dual-timescale adaptation mechanism while achieving low-cost robotic deployment with a cache-efficient replay strategy.
Yao He, Gan Sun, Wen-Qi Liang et al.
· arXiv.org · 2 citations