SOURCE-LINKED INTELLIGENCE

Learning Counterfactual World Models for Embodied Reasoning under Partial Observability

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the representations beneath such models are pretrained on large-scale video, interaction, and multimodal corpora, which raises a question prediction quality alone cannot answer: when is a learned representation actually actionable? We identify a failure mode we call counterfactual collapse: a model predicts visually plausible futures while failing to distinguish interventions with different behavioral consequences. This arises whenever a representat

Read original source ↗ Open in workspace

recordType

paper

region

Global