HumanEgo shows that a single 30‑minute egocentric video captured with a wearable Aria camera can train a dual‑arm robot to achieve 92.5% success on four real‑world tasks, transfer zero‑shot across robots, cameras and environments, and outperform tele‑operation while requiring far less data.
The PSI Lab at USC, led by Wang Yue, secured three CVPR 2026 awards—Psi‑0, PhysWorld and Humanoid Everyday—each tackling a distinct stage of humanoid robot learning: large‑scale human video pre‑training, embodiment‑aligned fine‑tuning, and physics‑aware world modeling, together forming a coherent data‑model‑prediction pipeline.
DexJoCo, a new MuJoCo‑based benchmark from the Chinese Academy of Sciences, introduces 11 complex dexterous‑hand tasks spanning tool use, bimanual collaboration, long‑horizon execution, and reasoning, and reveals that even state‑of‑the‑art robot learning models still struggle with reliable fine‑grained manipulation.
This article surveys recent advances in robot world models, explaining why predictive models are essential for embodied intelligence, how they integrate with Vision‑Language‑Action systems, the various architectural approaches, benchmark trends, and the remaining challenges for reliable deployment.
In a detailed interview, Ted Xiao, former Google DeepMind researcher, walks through the existence‑proof, foundation‑model, and scaling eras of embodied robot learning, explaining the technical challenges, pivotal decisions, and the evolving role of large language and vision models in robotics.
