SOURCE-LINKED INTELLIGENCE

LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

Counterfactual world models (CWM) extract motion from pretrained video predictors by comparing factual and intervened predictions. However, responses generated under different target-frame masks vary in reliability, while uniform aggregation weights them equally. We formulate response aggregation as candidate reliability learning and propose LPA-CWM with a lightweight Learned Physical Adjudicator (LPA). Trained on dense MOVi-F trajectories, the 3.0M-parameter LPA compares visual context and response structure across an unordered candidate set to predict relative weights, while the CWM predicto

Read original source ↗ Open in workspace

recordType

paper

region

Global