# Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

arXiv: https://arxiv.org/abs/2602.01591 · HTML: https://mlsanity.com/paper/2602.01591/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 34 of its 43 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 34)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [Directly Fine-Tuning Diffusion Models on Differentiable Rewards](https://mlsanity.com/paper/2309.17400/) (2023)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation](https://mlsanity.com/paper/2403.12015/) (2024)
- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE](https://mlsanity.com/paper/2507.21802/) (2025)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://mlsanity.com/paper/2501.18427/) (2025)
- [Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis](https://mlsanity.com/paper/2404.13686/) (2024)
- [ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation](https://mlsanity.com/paper/2406.02540/) (2024)
- [TempFlow-GRPO: When Timing Matters for GRPO in Flow Models](https://mlsanity.com/paper/2508.04324/) (2025)
- [Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning](https://mlsanity.com/paper/2508.20751/) (2025)
- [SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://mlsanity.com/paper/2503.09641/) (2025)
- [Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization](https://mlsanity.com/paper/2406.04314/) (2024)
- [Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models](https://mlsanity.com/paper/2509.25050/) (2025)
- [Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization](https://mlsanity.com/paper/2502.01051/) (2025)
- [Reward Guided Latent Consistency Distillation](https://mlsanity.com/paper/2403.11027/) (2024)
- [Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards](https://mlsanity.com/paper/2503.11240/) (2025)
- [Diff-Instruct++: Training One-step Text-to-image Generator Model to Align with Human Preferences](https://mlsanity.com/paper/2410.18881/) (2024)
- [Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization](https://mlsanity.com/paper/2410.03190/) (2024)
- [Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models](https://mlsanity.com/paper/2505.11245/) (2025)

## Built on by (most cited first, 4 of 4)

- [RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO](https://mlsanity.com/paper/2605.15190/) (2026)
- [DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing](https://mlsanity.com/paper/2603.28713/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL](https://mlsanity.com/paper/2609.03528/) (2026)

## Abstract (arXiv)

Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators. However, existing RL-based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address these limitations, we propose Temperature-Annealed Few-step Sampling with Group Relative Policy Optimization (TAFS-GRPO), a novel framework for training flow matching text-to-image models into efficient few-step generators well aligned with human preferences. Our method iteratively injects adaptive time-dependent noise into one-step clean predictions. By repeatedly annealing the model's sampled outputs, it introduces stochasticity into the sampling process while preserving the semantic integrity of each generated image. Moreover, its step-aware advantage integration mechanism combines GRPO with temperature-annealed sampling to eliminate the need for a differentiable reward function and provide dense, step-specific rewards for stable policy optimization. Extensive experiments demonstrate that TAFS-GRPO achieves strong performance in few-step text-to-image generation and significantly improves the alignment of generated images with human preferences. The code and models of this work will be available to facilitate further research.