# EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling

arXiv: https://arxiv.org/abs/2509.23909 · HTML: https://mlsanity.com/paper/2509.23909/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 46 of its 58 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- 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 46)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [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)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [OmniGen: Unified Image Generation](https://mlsanity.com/paper/2409.11340/) (2024)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [OmniGen2: Towards Instruction-Aligned Multimodal Generation](https://mlsanity.com/paper/2506.18871/) (2025)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [ImgEdit: A Unified Image Editing Dataset and Benchmark](https://mlsanity.com/paper/2505.20275/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)

## Built on by (most cited first, 30 of 64)

- [Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback](https://mlsanity.com/paper/2510.16888/) (2025)
- [Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance](https://mlsanity.com/paper/2603.02175/) (2026)
- [EditThinker: Unlocking Iterative Reasoning for Any Image Editor](https://mlsanity.com/paper/2512.05965/) (2025)
- [Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image](https://mlsanity.com/paper/2512.16899/) (2025)
- [MIRA: Multimodal Iterative Reasoning Agent for Image Editing](https://mlsanity.com/paper/2511.21087/) (2025)
- [VIVA: VLM-Guided Instruction-Based Video Editing with Reward Optimization](https://mlsanity.com/paper/2512.16906/) (2025)
- [GEditBench v2: A Human-Aligned Benchmark for General Image Editing](https://mlsanity.com/paper/2603.28547/) (2026)
- [ThinkGen: Generalized Thinking for Visual Generation](https://mlsanity.com/paper/2512.23568/) (2025)
- [Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation](https://mlsanity.com/paper/2603.12247/) (2026)
- [Leveraging Verifier-Based Reinforcement Learning in Image Editing](https://mlsanity.com/paper/2604.27505/) (2026)
- [Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria](https://mlsanity.com/paper/2605.08354/) (2026)
- [Group Relative Attention Guidance for Image Editing](https://mlsanity.com/paper/2510.24657/) (2025)
- [UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning](https://mlsanity.com/paper/2511.14760/) (2025)
- [PaCo-RL: Advancing Reinforcement Learning for Consistent Image Generation with Pairwise Reward Modeling](https://mlsanity.com/paper/2512.04784/) (2025)
- [MotionEdit: Benchmarking and Learning Motion-Centric Image Editing](https://mlsanity.com/paper/2512.10284/) (2025)
- [SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning](https://mlsanity.com/paper/2602.07458/) (2026)
- [LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models](https://mlsanity.com/paper/2602.14147/) (2026)
- [RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing](https://mlsanity.com/paper/2603.19206/) (2026)
- [Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling](https://mlsanity.com/paper/2605.13062/) (2026)
- [ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement](https://mlsanity.com/paper/2512.13303/) (2025)
- [Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling](https://mlsanity.com/paper/2604.28185/) (2026)
- [GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?](https://mlsanity.com/paper/2602.06013/) (2026)
- [EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing](https://mlsanity.com/paper/2603.14916/) (2026)
- [Image Diffusion Preview with Consistency Solver](https://mlsanity.com/paper/2512.13592/) (2025)
- [Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models](https://mlsanity.com/paper/2602.07533/) (2026)
- [CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Learning](https://mlsanity.com/paper/2602.14068/) (2026)
- [CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions](https://mlsanity.com/paper/2603.26174/) (2026)
- [DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing](https://mlsanity.com/paper/2604.25477/) (2026)
- [DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation](https://mlsanity.com/paper/2607.02220/) (2026)
- [Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes](https://mlsanity.com/paper/2601.02356/) (2026)

## Abstract (arXiv)

Instruction-guided image editing has achieved remarkable progress, yet current models still face challenges with complex instructions and often require multiple samples to produce a desired result. Reinforcement Learning (RL) offers a promising solution, but its adoption in image editing has been severely hindered by the lack of a high-fidelity, efficient reward signal. In this work, we present a comprehensive methodology to overcome this barrier, centered on the development of a state-of-the-art, specialized reward model. We first introduce EditReward-Bench, a comprehensive benchmark to systematically evaluate reward models on editing quality. Building on this benchmark, we develop EditScore, a series of reward models (7B-72B) for evaluating the quality of instruction-guided image editing. Through meticulous data curation and filtering, EditScore effectively matches the performance of learning proprietary VLMs. Furthermore, coupled with an effective self-ensemble strategy tailored for the generative nature of EditScore, our largest variant even surpasses GPT-5 in the benchmark. We then demonstrate that a high-fidelity reward model is the key to unlocking online RL for image editing. Our experiments show that, while even the largest open-source VLMs fail to provide an effective learning signal, EditScore enables efficient and robust policy optimization. Applying our framework to a strong base model, OmniGen2, results in a final model that shows a substantial and consistent performance uplift. Overall, this work provides the first systematic path from benchmarking to reward modeling to RL training in image editing, showing that a high-fidelity, domain-specialized reward model is the key to unlocking the full potential of RL in this domain.