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

2026-09-19

AI Summary

为了解决物理动态预测问题，CausalWM通过因果链式思维推理和三阶段训练方法，从视觉观察中学习并预测未来动态，达到领先性能。

Abstract

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-scale video pre-training, causal CoT mid-training, and multi-objective RL post-training. Despite using only a limited set of supervised CoT variables, CausalWM exhibits emergent in-context learning capabilities, enabling contextual visual feature guidance and efficient few-step generation. CausalWM achieves state-of-the-art performance across language-conditioned, action-conditioned, single-view and multi-view benchmarks, including Top-1 performance on TriWorldBench leaderboard.

Problem

• Causal Chain-of-Thought Reasoning
• Embodied World Model
• Physical Dynamics Prediction

Innovation

• Causal Chain-of-Thought Reasoning
• Embodied World Model
• Three-Stage Training Paradigm
• In-context Learning