AIBullisharXiv – CS AI · 10h ago7/10
🧠
Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
Researchers introduce GLAM (Grounded Latent-Action World Models), a machine learning framework that learns unified action representations across heterogeneous data sources with different action spaces and missing labels. The approach achieves 48% average improvement in task success rates for robotic manipulation tasks by grounding latent actions in environmental prediction rather than relying on hand-engineered alignment techniques.