用因果结构提升世界模型的反事实预测能力，让系统更懂干预后的变化。
CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
- 在潜空间中加入因果变分自编码器模块，增强对干预的感知能力。
- 物理基准上反事实命中率提升超100%，最高达272.7%。
- 能还原真实的物理作用关系，适合需要可解释性的场景。
本文提出将因果变分自编码器（CausalVAE）作为即插即用模块嵌入潜空间世界模型，并与多种编码器-转移结构结合。在多个基准测试中，该模块在保持事实预测性能的同时，显著提升了干预感知的反事实检索效果，表明其在分布偏移和干预下的更强鲁棒性。在物理基准上表现最佳：8个基线平均下，反事实命中率（CF-H@1）提升102.5%；在代表性GNN-NLL设置中，从11.0升至41.0，增幅达272.7%。通过因果分析发现，学习到的结构依赖关系能有效恢复一阶物理交互趋势，验证了潜空间因果结构的可解释性。
原文摘要 · Abstract (English)
In this work, CausalVAE is introduced as a plug-in structural module for latent world models and is attached to diverse encoder-transition backbones. Across the reported benchmarks, competitive factual prediction is preserved and intervention-aware counterfactual retrieval is improved after the plug-in is added, suggesting stronger robustness under distribution shift and interventions. The largest gains are observed on the Physics benchmark: when averaged over 8 paired baselines, CF-H@1 is improved by +102.5%. In a representative GNN-NLL setting on Physics, CF-H@1 is increased from 11.0 to 41.0 (+272.7%). Through causal analysis, learned structural dependencies are shown to recover meaningful first-order physical interaction trends, supporting the interpretability of the learned latent causal structure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。