Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Paper • 2608.26103 • Published • 26
robot
-
-
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Paper • 2608.27550 • Published • 91 -
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Paper • 2608.27549 • Published • 50 -
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Paper • 2608.25518 • Published • 196 -
The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
Paper • 2608.22301 • Published -
Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Paper • 2603.16666 • Published • 2 -
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Paper • 2609.02886 • Published • 139