# OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning

arXiv: https://arxiv.org/abs/2508.21066 · HTML: https://mlsanity.com/paper/2508.21066/

## Key facts

- Cited by 23 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 29 of its 33 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)
- Deep reinforcement learning methods / [RL with diffusion and flow models](https://mlsanity.com/deeprl/rl-with-diffusion-and-flow-models/)

## Builds on (most cited first, 29 of 29)

- [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)
- [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)
- [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)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [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)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Improving Video Generation with Human Feedback](https://mlsanity.com/paper/2501.13918/) (2025)
- [Seedance 1.0: Exploring the Boundaries of Video Generation Models](https://mlsanity.com/paper/2506.09113/) (2025)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback](https://mlsanity.com/paper/2404.07987/) (2024)
- [Seedream 3.0 Technical Report](https://mlsanity.com/paper/2504.11346/) (2025)
- [Inst-Inpaint: Instructing to Remove Objects with Diffusion Models](https://mlsanity.com/paper/2304.03246/) (2023)
- [OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization](https://mlsanity.com/paper/2412.15159/) (2024)
- [ByteEdit: Boost, Comply and Accelerate Generative Image Editing](https://mlsanity.com/paper/2404.04860/) (2024)

## Built on by (most cited first, 23 of 23)

- [Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback](https://mlsanity.com/paper/2510.16888/) (2025)
- [EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling](https://mlsanity.com/paper/2509.23909/) (2025)
- [EditThinker: Unlocking Iterative Reasoning for Any Image Editor](https://mlsanity.com/paper/2512.05965/) (2025)
- [Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling](https://mlsanity.com/paper/2509.23352/) (2025)
- [Leveraging Verifier-Based Reinforcement Learning in Image Editing](https://mlsanity.com/paper/2604.27505/) (2026)
- [RubricRL: Simple Generalizable Rewards for Text-to-Image Generation](https://mlsanity.com/paper/2511.20651/) (2025)
- [Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning](https://mlsanity.com/paper/2512.09924/) (2025)
- [Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models](https://mlsanity.com/paper/2601.20305/) (2026)
- [SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning](https://mlsanity.com/paper/2602.07458/) (2026)
- [Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling](https://mlsanity.com/paper/2602.11146/) (2026)
- [Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling](https://mlsanity.com/paper/2604.28185/) (2026)
- [RewardHarness: Self-Evolving Agentic Post-Training](https://mlsanity.com/paper/2605.08703/) (2026)
- [RePainter: Empowering E-commerce Object Removal via Spatial-matting Reinforcement Learning](https://mlsanity.com/paper/2510.07721/) (2025)
- [Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models](https://mlsanity.com/paper/2602.07533/) (2026)
- [DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing](https://mlsanity.com/paper/2604.25477/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On](https://mlsanity.com/paper/2603.05659/) (2026)
- [An Evolutionary Agentic Approach for Open-ended Image Quality Perception](https://mlsanity.com/paper/2609.22942/) (2026)
- [Beyond Pixels: Benchmarking and Reward-Based Assessing Framework for Visual Spatial Aesthetics](https://mlsanity.com/paper/2512.05098/) (2025)
- [Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models](https://mlsanity.com/paper/2602.22227/) (2026)
- [Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing](https://mlsanity.com/paper/2605.16951/) (2026)
- [Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation](https://mlsanity.com/paper/2607.11886/) (2026)
- [Scalable Minimal-Change Learning for Controllable Image Editing](https://mlsanity.com/paper/2610.06021/) (2026)

## Abstract (arXiv)

In this paper, we introduce OneReward, a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks under different evaluation criteria using only textitOne Reward model. By employing a single vision-language model (VLM) as the generative reward model, which can distinguish the winner and loser for a given task and a given evaluation criterion, it can be effectively applied to multi-task generation models, particularly in contexts with varied data and diverse task objectives. We utilize OneReward for mask-guided image generation, which can be further divided into several sub-tasks such as image fill, image extend, object removal, and text rendering, involving a binary mask as the edit area. Although these domain-specific tasks share same conditioning paradigm, they differ significantly in underlying data distributions and evaluation metrics. Existing methods often rely on task-specific supervised fine-tuning (SFT), which limits generalization and training efficiency. Building on OneReward, we develop Seedream 3.0 Fill, a mask-guided generation model trained via multi-task reinforcement learning directly on a pre-trained base model, eliminating the need for task-specific SFT. Experimental results demonstrate that our unified edit model consistently outperforms both commercial and open-source competitors, such as Ideogram, Adobe Photoshop, and FLUX Fill [Pro], across multiple evaluation dimensions. Code and model are available at: https://one-reward.github.io