GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
Classification
View four quadrants- Major category
- WAMs
- Quadrant
- Q4 · Dual-system × IDM
- Architecture
- Dual-system
- Prediction paradigm
- IDM
- Subcategories
- Visual planning & IDM
- Source review status
- Not assigned
Category review. A visual future generator feeds a distinct inverse-dynamics model that converts predicted futures into robot action chunks, with candidate supervision selected for action compatibility. Separate future generator and IDM map generated futures into physical actions. Reading evidence
Contribution
GE-Act 2.0 connects a compact visual representation, a one-step future generator, and a separate inverse dynamics model. Its central training problem is pairing generated futures with compatible recorded actions. KASO selects futures using the current action model before updating both modules. Real-robot experiments show broader manipulation capability as co-training data grows, with persistent weaknesses in fine manipulation and ordinal language; simulation comparisons use a separate adaptation protocol.
Abstract
An abstract has not been added yet.
Affiliations
Not listed in the collection.