发表机构
University of Washington（华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出LeFlow，它从世界模型学习可复用潜在轨迹先验，将规划转为条件潜在轨迹生成，在四个目标条件像素控制基准中提升规划成功率并大幅减少规划时间。
AI 中文摘要
潜在世界模型是将图像像素转换为潜在嵌入的强大编码器，但现有世界模型仍依赖在线轨迹优化进行动作规划：对于每一个状态-目标对，都会从零开始运行迭代优化器以搜索最优动作序列，将世界模型视为黑箱模拟器。这种方法在每次重新规划步骤中都会重新付出全部迭代优化的代价，且不会在不同查询间复用任何规划经验。本研究探究在学习到潜在世界模型后，规划本身是否可以被摊销。我们提出LeFlow，它从世界模型中学习直接在潜在动力学空间运行的可复用潜在轨迹先验。LeFlow将规划重构为条件潜在轨迹生成：整流流模型在当前和目标嵌入之间生成未来潜在路径，逆动力学解码器将潜在转换转化为动作块，冻结的世界模型通过自回归滚动验证每个候选方案。在四个主要的目标条件像素控制基准测试中，LeFlow用摊销潜在规划和固定预算滚动选择取代了迭代动作空间优化，实现了一致的成功率提升，且规划时间减少了一个数量级以上。我们的结果表明，潜在世界模型不仅应支持预测，还应支持可复用规划先验。我们的代码可在this https URL获取。
英文摘要
Latent world models are inherently strong encoders that transform image pixel to latent embedding, yet existing world models still rely on online trajectory optimization for action planning: for every state-goal pair, an iterative optimizer is run from scratch to search for optimal action sequences, treating the world model as a black-box simulator. This approach pays the full iterative optimization cost anew at every replanning step and reuses no planning experience across queries. In this work, we ask whether planning itself can be amortized once a latent world model has been learned. We present LeFlow, which learns a reusable latent trajectory prior operating directly in the latent dynamics space from the world model. LeFlow recasts planning as conditional latent trajectory generation: a rectified-flow model imagines a future latent path between the current and goal embeddings, an inverse dynamics decoder turns latent transitions into action chunks, and the frozen world model verifies each candidate by autoregressive rollout. Across four major goal-conditioned pixel-control benchmarks, LeFlow replaces iterative action-space optimization with amortized latent planning and fixed-budget rollout selection, achieving consistent success-rate gains with an order-of-magnitude reduction in planning time. Our results argue that latent world models should support not only prediction but reusable planning priors. Our code is available at https://github.com/hsiangwei0903/LeFlow.
