SOURCE-LINKED INTELLIGENCE

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning. In large language models, a novel task can be performed simply by specifying it in the context, without any parameter update. This form of in-context learning (ICL) turns generalization into a problem of task specification. To achieve cross-task generalization, we bring this paradigm to robotic manipulation, and argue that the natural task specification for manipulation is a human video: unlike language, it provides rich visual cues abou

Read original source ↗ Open in workspace

recordType

paper

region

Global