Skip to content
Research

MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators.

arXiv:2609.37670v1 Announce Type: new Abstract: MeanFlow enables efficient few-step generation by predicting interval-average velocities, but this representation creates a mismatch for reward fine-tuning: existing advantage-based objectives are typically defin

arXiv cs.AIResearch source·