# BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models

arXiv: https://arxiv.org/abs/2509.06040 · HTML: https://mlsanity.com/paper/2509.06040/

## Key facts

- Cited by 61 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 41 references that are in the map.
- First posted on arXiv 7 Sep 2025.

## 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)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (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)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [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)
- [Aligning Text-to-Image Diffusion Models with Reward Backpropagation](https://mlsanity.com/paper/2310.03739/) (2023)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [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)
- [VideoDPO: Omni-Preference Alignment for Video Diffusion Generation](https://mlsanity.com/paper/2412.14167/) (2024)
- [TempFlow-GRPO: When Timing Matters for GRPO in Flow Models](https://mlsanity.com/paper/2508.04324/) (2025)
- [Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation](https://mlsanity.com/paper/2402.10210/) (2024)

## Built on by (most cited first, 30 of 61)

- [Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models](https://mlsanity.com/paper/2509.25050/) (2025)
- [Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning](https://mlsanity.com/paper/2512.24146/) (2025)
- [DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO](https://mlsanity.com/paper/2512.21514/) (2025)
- [π_textttRL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models](https://mlsanity.com/paper/2510.25889/) (2025)
- [Neighbor GRPO: Contrastive ODE Policy Optimization Aligns Flow Models](https://mlsanity.com/paper/2511.16955/) (2025)
- [Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders](https://mlsanity.com/paper/2601.10332/) (2026)
- [Manifold-Aware Exploration for Reinforcement Learning in Video Generation](https://mlsanity.com/paper/2603.21872/) (2026)
- [Principled RL for Flow Matching Emerges from the Chunk-level Policy Optimization](https://mlsanity.com/paper/2510.21583/) (2025)
- [E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models](https://mlsanity.com/paper/2601.00423/) (2026)
- [Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models](https://mlsanity.com/paper/2510.02654/) (2025)
- [WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning](https://mlsanity.com/paper/2602.17025/) (2026)
- [TAGRPO: Boosting GRPO on Image-to-Video Generation with Direct Trajectory Alignment](https://mlsanity.com/paper/2601.05729/) (2026)
- [Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning](https://mlsanity.com/paper/2605.02913/) (2026)
- [Video Models Can Reason with Verifiable Rewards](https://mlsanity.com/paper/2605.15458/) (2026)
- [Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards](https://mlsanity.com/paper/2512.00743/) (2025)
- [PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling](https://mlsanity.com/paper/2512.04784/) (2025)
- [OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models](https://mlsanity.com/paper/2604.04142/) (2026)
- [Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models](https://mlsanity.com/paper/2604.17415/) (2026)
- [V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think](https://mlsanity.com/paper/2604.23380/) (2026)
- [RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO](https://mlsanity.com/paper/2605.15190/) (2026)
- [ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.03425/) (2026)
- [LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories](https://mlsanity.com/paper/2604.15311/) (2026)
- [ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement](https://mlsanity.com/paper/2512.13303/) (2025)
- [Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation](https://mlsanity.com/paper/2601.12401/) (2026)
- [AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models](https://mlsanity.com/paper/2602.06825/) (2026)
- [Diffusion Reinforcement Learning via Centered Reward Distillation](https://mlsanity.com/paper/2603.14128/) (2026)
- [A Systematic Post-Train Framework for Video Generation](https://mlsanity.com/paper/2604.25427/) (2026)
- [Embedding-perturbed Exploration Preference Optimization for Flow Models](https://mlsanity.com/paper/2605.15803/) (2026)
- [SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models](https://mlsanity.com/paper/2512.22170/) (2025)
- [HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models](https://mlsanity.com/paper/2601.15968/) (2026)

## Abstract (arXiv)

Recent progress in aligning image and video generative models with Group Relative Policy Optimization (GRPO) has improved human preference alignment, but existing variants remain inefficient due to sequential rollouts and large numbers of sampling steps, unreliable credit assignment: sparse terminal rewards are uniformly propagated across timesteps, failing to capture the varying criticality of decisions during denoising. In this paper, we present BranchGRPO, a method that restructures the rollout process into a branching tree, where shared prefixes amortize computation and pruning removes low-value paths and redundant depths. BranchGRPO introduces three contributions: (1) a branching scheme that amortizes rollout cost through shared prefixes while preserving exploration diversity; (2) a reward fusion and depth-wise advantage estimator that transforms sparse terminal rewards into dense step-level signals; and (3) pruning strategies that cut gradient computation but leave forward rollouts and exploration unaffected. On HPDv2.1 image alignment, BranchGRPO improves alignment scores by up to 16% over DanceGRPO, while reducing per-iteration training time by nearly 55%. A hybrid variant, BranchGRPO-Mix, further accelerates training to 4.7x faster than DanceGRPO without degrading alignment. On WanX video generation, it further achieves higher Video-Align scores with sharper and temporally consistent frames compared to DanceGRPO. Codes are available at hrefhttps://fredreic1849.github.io/BranchGRPO-Webpage/BranchGRPO.