Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models

2026-08-27

AI Summary

研究通过引入Latent Evolution Operator Network(LEON)，采用基于操作符的传播和加性强迫方法，在隐空间中改善了世界行动模型中的状态演变预测问题。

Abstract

World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction. Recent WAMs increasingly perform such prediction in latent representation spaces, avoiding full appearance-level generation while preserving control-relevant information. Yet latent transitions are commonly realized with Transformer-based predictors whose inductive structure is centered on token interaction rather than temporal evolution. We study transition realization as an architectural choice distinct from predictive representation and prediction-policy coupling. We introduce the Latent Evolution Operator Network (LEON), which models latent evolution in a learned observable space through context-modulated operator-based propagation and additive forcing. Grounded in the controlled Koopman generator view of evolution, LEON organizes context-dependent transition variation around a shared evolution-operator structure while retaining a complementary path for additive change. Controlled dynamical systems verify the resulting evolution-specific inductive bias and the complementary roles of operator propagation and forcing. Across two WAM formulations that integrate latent prediction into the policy differently, LEON improves closed-loop performance and robustness while remaining effective under full transition replacement. These results establish transition realization as a consequential architectural choice in latent WAMs.

Problem

• World Action Models
• latent transitions
• temporal evolution
• Transformer-based predictors

Innovation

• Latent Evolution
• Operator-based Propagation
• Additive Forcing
• Koopman Generator
• World Action Models