arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.07712cs.LG
收藏

CausalVAE作为世界模型的插件:迈向可靠的反事实动力学

CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics

Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);The University of Hong Kong(香港大学);INFIFORCE Intelligent Technology(INFIFORCE智能科技)

Ziyi Ding, Xianxin Lai, Weiyu Chen, Xiao-Ping Zhang, Jiayu Chen

AI总结:

本文提出CausalVAE作为潜在世界模型的插件模块,通过增强事实预测和反事实检索,提升模型在分布偏移和干预下的鲁棒性,尤其在物理基准上取得显著提升。

摘要:

在本工作中,CausalVAE被引入作为潜在世界模型的插件结构模块,并附加于多种编码器-转移回骨上。在报告的基准测试中,添加插件后保持了竞争性的事实预测,并提高了干预感知的反事实检索,表明在分布偏移和干预下具有更强的鲁棒性。最大的收益观察到在物理基准上:当平均8对基线时,CF-H@1提高了+102.5%。在物理基准上的代表性GNN-NLL设置中,CF-H@1从11.0增加到41.0(+272.7%)。通过因果分析,学习到的结构依赖性被展示为恢复有意义的一阶物理相互作用趋势,支持了学习到的潜在因果结构的可解释性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑