# Personalize at Test Time: Learning User Preferences for Image Generation

arXiv: https://arxiv.org/abs/2610.09015 · HTML: https://mlsanity.com/paper/2610.09015/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 28 of its 63 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 28 of 28)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (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)
- [Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack](https://mlsanity.com/paper/2309.15807/) (2023)
- [Seedream 4.0: Toward Next-generation Multimodal Image Generation](https://mlsanity.com/paper/2509.20427/) (2025)
- [MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE](https://mlsanity.com/paper/2507.21802/) (2025)
- [Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment](https://mlsanity.com/paper/2402.10207/) (2024)
- [Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization](https://mlsanity.com/paper/2406.04314/) (2024)
- [Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback](https://mlsanity.com/paper/2510.16888/) (2025)
- [Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization](https://mlsanity.com/paper/2406.06382/) (2024)
- [Training-free Diffusion Model Alignment with Sampling Demons](https://mlsanity.com/paper/2410.05760/) (2024)
- [Language Model Personalization via Reward Factorization](https://mlsanity.com/paper/2503.06358/) (2025)
- [Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models](https://mlsanity.com/paper/2505.11245/) (2025)
- [Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance](https://mlsanity.com/paper/2508.21016/) (2025)
- [MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models](https://mlsanity.com/paper/2510.01549/) (2025)
- [One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment](https://mlsanity.com/paper/2601.18731/) (2026)
- [AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models](https://mlsanity.com/paper/2602.06825/) (2026)
- [Personalized Reward Modeling for Text-to-Image Generation](https://mlsanity.com/paper/2511.19458/) (2025)
- [EXACT: Explicit Attribute-Guided Decoding-Time Personalization](https://mlsanity.com/paper/2602.17695/) (2026)
- [CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation](https://mlsanity.com/paper/2601.06352/) (2026)
- [Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance](https://mlsanity.com/paper/2602.18799/) (2026)
- [Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation](https://mlsanity.com/paper/2603.20725/) (2026)
- [PrefReward: Learning User Preference Matrix for Personalized Text Generation](https://mlsanity.com/paper/2607.21067/) (2026)
- [Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization](https://mlsanity.com/paper/2608.12389/) (2026)
- [Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM](https://mlsanity.com/paper/2609.04738/) (2026)
- [Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models](https://mlsanity.com/paper/2609.05968/) (2026)

## Abstract (arXiv)

Diffusion models can generate high-quality images, yet aligning their outputs with individual user preferences remains challenging. A key bottleneck is accurately modeling diverse user preferences from limited feedback. Existing approaches often rely on labor-intensive manual preference annotations or vision-language models (VLM) to extract preference information from user interaction histories, introducing substantial annotation or computational costs that limit scalability. We propose an approach that learns personalized reward models directly from users' historical image preference pairs. First, we use an autoencoder to compress hundreds of visual attributes into 50 attribute-anchored preference dimensions and train an evaluator to score images along these dimensions. We then represent each user's preferences as a linear combination of the shared dimension scores, estimating the user-specific weights by maximizing the likelihood of their observed pairwise preferences under the Bradley-Terry model. This formulation reduces per-user adaptation to optimizing a low-dimensional weight vector, simplifying optimization and enabling data-efficient personalization from sparse feedback. The learned personalized rewards guide image generation at inference time while keeping the diffusion model frozen. Experiments on real-user preference data show that our approach achieves approximately 77% held-out pairwise preference prediction accuracy and improves the alignment of generated images with individual user preferences.