# Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models

arXiv: https://arxiv.org/abs/2605.06070 · HTML: https://mlsanity.com/paper/2605.06070/

## Key facts

- No citing papers in the map yet (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 7 May 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)

- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [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)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (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)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [Aligning Diffusion Models by Optimizing Human Utility](https://mlsanity.com/paper/2404.04465/) (2024)
- [Margin-aware Preference Optimization for Aligning Diffusion Models without Reference](https://mlsanity.com/paper/2406.06424/) (2024)
- [Scalable Ranked Preference Optimization for Text-to-Image Generation](https://mlsanity.com/paper/2410.18013/) (2024)
- [Getting it Right: Improving Spatial Consistency in Text-to-Image Models](https://mlsanity.com/paper/2404.01197/) (2024)

## Abstract (arXiv)

Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct preference optimization (DPO), which avoids explicit reward modeling, has been widely studied. However, its reliance on binary feedback limits it to coarse-grained modeling on chosen-rejected pairs, resulting in suboptimal optimization. In this paper, we propose ArenaPO, which leverages Arena scores as offline rewards to provide refined feedback, thus achieving efficient and fine-grained optimization without a reward model. This enables ArenaPO to benefit from both the rich rewards of traditional RLHF and the efficiency of DPO. Specifically, we first construct a model Arena in which each model's capability is represented as a Gaussian distribution, and infer these capabilities by traversing the annotated pairwise preferences. Each output image is treated as a sample from the corresponding capability distribution. Then, for a image pair, conditioned on the two capability distributions and the observed pairwise preference, the absolute quality gap is estimated using latent-variable inference based on truncated normal distribution, which serves as fine-grained feedback during training. It does not require a reward model and can be computed offline, thus introducing no additional training overhead. We conduct ArenaPO training on Pick-a-Pic v2 and HPD v3 datasets, showing that ArenaPO consistently outperforms existing baselines.