GALA

“GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments”

“existing image-based LAMs often fail to capture fine-grained end-effector articulation, particularly finger-level geometric changes in human and dexterous robot hands”

“68.3% RoboCasa-GR1 success rate and 75.5% real-world success rate”