MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an efficient forward-process RL framework that does not require reverse-process trajectories or likelihood estimation. However, applying such RL methods to MeanFlow remains underexplored. DiffusionNFT optimizes instantaneous velocities, whereas MeanFlow samples with av
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) · 59%Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment →
- PossiblePossibly related (embedding) · 51%Understand diffusion in 20 minutes →
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- LinkedLinked via arxiv author · 85%Yushi Huang →
“MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators”
- LinkedLinked via arxiv author · 85%Xiangxin Zhou →
“MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators”
- LinkedLinked via arxiv author · 85%Weijun Zhang →
“MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators”
- LinkedLinked via arxiv author · 85%Liefeng Bo →
“MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators”
- LinkedLinked via arxiv author · 85%Tianyu Pang →
“MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators”