SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled interaction. Most inherit pretrained video generators, leaving WAM pretraining and scaling underexplored. We introduce Genie Envisioner Act 2.0 (GE-Act 2.0), a world-action model whose trainable generative and action components are all initialized from scratch on manipulation data. It combines a control-oriented autoencoder (CoAE), a single-step visual planner (SVP), and an inverse dynamics model (IDM). CoAE retains action- and instruction-relevant informatio

Read original source ↗ Open in workspace

recordType

paper

region

Global