LeFlow: Generative Latent Flow Planning for World Models
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%Gradient-based Planning for World Models at Longer Horizons →
- FuzzySimilar title/name (fuzzy) · 84%GoogleCloudPlatform/generative-ai →
“Fuzzy title match (0.92): “LeFlow: Generative Latent Flow Planning for World Models” ≈ “GoogleCloudPlatform/generative-ai””
- FuzzySimilar title/name (fuzzy) · 59%steven2358/awesome-generative-ai →
“Fuzzy title match (0.73): “LeFlow: Generative Latent Flow Planning for World Models” ≈ “steven2358/awesome-generative-ai””
- LinkedLinked via arxiv author · 85%Hsiang-Wei Huang →
“LeFlow: Generative Latent Flow Planning for World Models”
- LinkedLinked via arxiv author · 85%Jianxu Shangguan →
“LeFlow: Generative Latent Flow Planning for World Models”
- LinkedLinked via arxiv author · 85%Junbin Lu →
“LeFlow: Generative Latent Flow Planning for World Models”
- LinkedLinked via arxiv author · 85%Jenq-Neng Hwang →
“LeFlow: Generative Latent Flow Planning for World Models”