ID-WM：分层世界模型提升长时程任务规划
Hierarchical World Models with Implicit Dynamics
新论文 ID-WM 用高低两层世界模型拆解长时程规划，比 diffusion 规划器提升 38.5%，做具身智能的可以看看。
一篇 arXiv 论文提出 ID-WM（Implicit Dynamics World Models），将状态空间可达性与局部控制解耦。高层模型在状态流形上采样可行转移，低层世界模型作为逆动力学求解器将其落地为具体动作。该方案在三个导航与操作测试套件中，比 SOTA 策略和 diffusion 规划器提升 38.5%，比单层世界模型 MPC 提升 135%。作者称这缓解了长时程任务中的累积误差问题。
Hierarchical World Models with Implicit Dynamics
Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks remain hindered by cumulative errors and search complexity. Existing hierarchical methods often use rigid macro-actions or latent skills, leading to brittle representations and limited fine-grained control. We introduce ID-WM (Implicit Dynamics World Models), a hierarchical world model that decouples state-space reachability from local control. Our framework utilizes a high-level model to sample feasible transitions across the state manifold and a low-level world model as an inverse dynamics solver to ground these transitions into precise actions. This allows the planner to identify reachable subgoals without being constrained by low-level execution details. By prioritizing local physical feasibility over global behavioral patterns, ID-WM synthesizes novel long-horizon plans from short segments, transcending the specific behavioral modes seen during training. We demonstrate its effectiveness across three navigation and manipulation suites, achieving a 38.5% improvement over state-of-the-art policy and diffusion-based planners. Crucially, by leveraging this hierarchical structure to mitigate compounding errors, our approach yields a 135% performance gain over single-level world model MPC, particularly in complex, unseen configurations for long-horizon tasks. Videos can be viewed at https://id-wm.github.io