Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

arXiv cs.LG1mo4 min read

arXiv:2607.00535v1 Announce Type: new Abstract: Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between noise and data. However, these models are typically deterministic, which makes them difficult to optimize with reinforcement learning (RL) post-training methods that require stochastic trajectories and well-defined likelihood ratios. Existing SDE-based stochasticization techniques are designed for velocity-based samplers with infinitesimal or finely discretized transitions, and therefore do not directly

Read the full story at arXiv cs.LG →

Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

More in Machine Learning

Reducing Human Annotation with ML Active Learning

Learning What Matters: Supervising Sparse Attention Routing with Causal Evidence Sets

On the Depth Scalability of Logic Gate Networks

Pretraining EHR Foundation Models with Patient-Aware Sampling

From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning

Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection