Action Compositional Training Enables VLA Models to Generalize Beyond Training DemonstrationsACT-VLA框架：VLA模型突破示范数据限制，实现动作组合
S 1.7T11 sources1 个来源R7-research
Researchers submit paper proposing ACT-VLA, an offline data augmentation framework for Vision-Language-Action models that enables composition of known sub-skills into novel behaviors without expanding datasets.
The framework uses the model's latent task representations to synthesize new, physically valid demonstrations, eliminating the need for additional manual data collection from costly human teleoperation.
By automatically expanding the training distribution, ACT-VLA mitigates VLA model overfitting to specific behavioral patterns and addresses the labor-intensive challenge of acquiring high-quality robot demonstration data.