SOURCE-LINKED INTELLIGENCE

CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly entangled within latent representations. We introduce CausalWM, a 16B embodied world model that performs explicit causal chain-of-thought reasoning before future video prediction. CausalWM organizes useful variables into a reasoning trajectory, allowing the model to progressively capture causal dependencies underlying physical evolution. To train CausalWM, we collect 31K hours embodied data and develop a three-stage paradigm consisting of large-sc

Read original source ↗ Open in workspace

recordType

paper

region

Global