Sep 2026
Imagine-RL: Residual-Confidence-Guided Cross-Attention for World-Model-Augmented VLA Reinforcement Learning
Imagine-RL is presented, which augments noise-space VLA post-training with action-conditioned visual-torque imagination and improves the average success rate by (23.6%) over DSRL and by (60%) over VLA baselines.
Ke-Jia Hu, Wen Zhai, Bo-Tong Zhao et al.
· arXiv.org · 1 citation