RESEARCH PAPER

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

AgiBot Research Team

Classification

View four quadrants
Major category
WAMs
Architecture
Dual-system
Prediction paradigm
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

AT A GLANCE

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.