Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Paper • 2608.26103 • Published • 19
robot
-
-
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Paper • 2608.27550 • Published • 55 -
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Paper • 2608.27549 • Published • 40 -
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Paper • 2608.25518 • Published • 185