Preprint
Aug 2026
TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models
TEMPO is proposed, a semantic-action decoupled, two-timescale RL post-training framework for VLA models that consistently outperforms both pretrained state-of-the-art VLA models and the RL post-training baseline, while reaching and maintaining higher evaluation rewards on two real-world tasks.
Ziheng Liu, Quan-Tao Yang
· 0 citations