# Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling

arXiv: https://arxiv.org/abs/2509.23352 · HTML: https://mlsanity.com/paper/2509.23352/

## Key facts

- Cited by 18 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 32 of its 35 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space](https://mlsanity.com/paper/2506.15742/) (2025)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [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)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2302.04867/) (2023)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE](https://mlsanity.com/paper/2507.21802/) (2025)
- [DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics](https://mlsanity.com/paper/2310.13268/) (2023)
- [TempFlow-GRPO: When Timing Matters for GRPO in Flow Models](https://mlsanity.com/paper/2508.04324/) (2025)
- [On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting](https://mlsanity.com/paper/2508.11408/) (2025)
- [SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL](https://mlsanity.com/paper/2504.11455/) (2025)
- [Towards a Unified View of Large Language Model Post-Training](https://mlsanity.com/paper/2509.04419/) (2025)
- [ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL](https://mlsanity.com/paper/2505.24875/) (2025)

## Built on by (most cited first, 18 of 18)

- [GARDO: Reinforcing Diffusion Models without Reward Hacking](https://mlsanity.com/paper/2512.24138/) (2025)
- [E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models](https://mlsanity.com/paper/2601.00423/) (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)
- [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)
- [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)
- [AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models](https://mlsanity.com/paper/2602.06825/) (2026)
- [TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment](https://mlsanity.com/paper/2605.10983/) (2026)
- [FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling](https://mlsanity.com/paper/2604.06916/) (2026)
- [Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping](https://mlsanity.com/paper/2605.10937/) (2026)
- [When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy](https://mlsanity.com/paper/2605.12112/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO](https://mlsanity.com/paper/2606.06828/) (2026)
- [Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On](https://mlsanity.com/paper/2607.21694/) (2026)
- [PosterText: Towards Unified Visual Text Generation and Editing for E-commerce Poster](https://mlsanity.com/paper/2608.16289/) (2026)
- [LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL](https://mlsanity.com/paper/2609.03528/) (2026)
- [Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization](https://mlsanity.com/paper/2609.34688/) (2026)

## Abstract (arXiv)

The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these gains often come at the cost of exhaustive exploration and inefficient sampling strategies due to slight variation in the sampling group. Building on this insight, we propose Dynamic-TreeRPO, which implements the sliding-window sampling strategy as a tree-structured search with dynamic noise intensities along depth. We perform GRPO-guided optimization and constrained Stochastic Differential Equation (SDE) sampling within this tree structure. By sharing prefix paths of the tree, our design effectively amortizes the computational overhead of trajectory search. With well-designed noise intensities for each tree layer, Dynamic-TreeRPO can enhance the variation of exploration without any extra computational cost. Furthermore, we seamlessly integrate Supervised Fine-Tuning (SFT) and RL paradigm within Dynamic-TreeRPO to construct our proposed LayerTuning-RL, reformulating the loss function of SFT as a dynamically weighted Progress Reward Model (PRM) rather than a separate pretraining method. By associating this weighted PRM with dynamic-adaptive clipping bounds, the disruption of exploration process in Dynamic-TreeRPO is avoided. Benefiting from the tree-structured sampling and the LayerTuning-RL paradigm, our model dynamically explores a diverse search space along effective directions. Compared to existing baselines, our approach demonstrates significant superiority in terms of semantic consistency, visual fidelity, and human preference alignment on established benchmarks, including HPS-v2.1, PickScore, and ImageReward. In particular, our model outperforms SoTA by 4.9%, 5.91%, and 8.66% on those benchmarks, respectively, while improving the training efficiency by nearly 50%.