Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
cs.LG, cs.AI, cs.CV
Submitted: 2026-07-01
Updated: 2026-09-27
Terminology
Sources
- Flow Matching in Latent Space
- Consistency Models Made Easy
- Mean Flows for One-step Generative Modeling
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
- Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
- How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
- MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
- Trajectory Consistency for One-Step Generation on Euler Mean Flows
- Flow Matching for Generative Modeling
- Flow Matching Guide and Code
- Strong Stochastic Flow Maps
- Meta Flow Maps enable scalable reward alignment
- Few-Step Distillation for Text-to-Image Generation: A Practical Guide
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- DanceGRPO: Unleashing GRPO on Visual Generation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks