Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Paper • 2608.26103 • Published • 25
robot
-
-
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Paper • 2608.27550 • Published • 70 -
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
Paper • 2608.27549 • Published • 47 -
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Paper • 2608.25518 • Published • 36 -
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 • 115 -
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning
Paper • 2609.03199 • Published • 13 -
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
Paper • 2606.19980 • Published • 15 -
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
Paper • 2609.05588 • Published • 40 -
Show-Harness: Just a VLM Agent Can Play Robots
Paper • 2609.10522 • Published • 102 -
Agent as Policy for Robotic Manipulation
Paper • 2609.12541 • Published • 17 -
Transferring the Intelligence of VLMs to Robotic Control
Paper • 2609.22966 • Published • 67 -
HuRo: Robotizing Human Videos for Scalable VLA Pretraining
Paper • 2609.10706 • Published • 29 -
In-Context Robot Learning with VLM Agents
Paper • 2609.19138 • Published • 28 -
InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
Paper • 2609.31394 • Published • 29 -
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 93 -
Real2Gym: Building Gyms from Videos, Bringing Skills to Robots
Paper • 2609.37089 • Published • 6 -
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
Paper • 2609.38173 • Published • 57 -
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
Paper • 2610.12468 • Published • 46 -
VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models
Paper • 2610.21306 • Published • 20 -
Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience
Paper • 2610.26855 • Published • 62 -
Learning from Fleet Experience: A Collective Learning Paradigm for Robots
Paper • 2610.25736 • Published • 127 -
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
Paper • 2610.32093 • Published • 32 -
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Paper • 2610.37666 • Published • 66