SOURCE-LINKED INTELLIGENCE

LeFlow: Generative Latent Flow Planning for World Models

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

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 pre

Read original source ↗ Open in workspace

recordType

paper

region

Global