世界モデルの解釈可能性：表現の解読から潜在世界の理解へ
World Model Interpretability: From Decoding Representations to Understanding Latent Worlds
JEPA型の潜在世界モデルについて、何を符号化しているかではなく潜在変数の相互作用・進化・因果的役割を理解するための「Ground・Structure・Verify・Act」の4段階研究アジェンダを提唱する展望論文。
著者: Jize Wang, Yongcheng Jing, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao
分類: cs.LG, cs.AI
原文アブストラクト
Emerging Joint-Embedding Predictive Architectures (JEPAs) are moving beyond representation learning towards latent world models that support prediction, planning, and control. Yet their latent worlds naturally lack a human-interpretable interface. In this Perspective, we argue that as JEPA latents become internal states for prediction and action, interpretability must move beyond what they encode to how latent variables interact, evolve, and causally drive prediction. To this end, we envision a four-stage research agenda, involving Ground, Structure, Verify, and Act, to guide this shift toward actionable latent-world understanding. Within our framework, existing JEPA interpretability efforts provide early evidence for Ground, while systematic analysis of latent structure, causal verification, and intervention remains largely unexplored. Overall, this Perspective aims to call for a broader latent-world interpretability agenda that shifts attention from decoding representations toward understanding, validating, and acting on latent worlds.