Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to reconcile fidelity and diversity, often hampered by distribution misalignment and overfitting, respectively.To mitigate this, we introduce Anomaly Preference Optimization,a novel paradigm that reformulates anomaly generation as a preference learning problem.Central to our approach is an implicit preference alignment mechanism that leverages real anomalies as positive references, deriving optimization signals directly from denoising trajectory deviations without requiring costly human annotation. Furthermore, we propose a Time-Aware Capacity Allocation module that dynamically distributes model capacity along the diffusion timeline,prioritizing structural diversity during highnoise phases while enhancing fine-grained fidelity in low-noise stages. During inference, a hierarchical sampling strategy modulates the coherencealignment trade-off, enabling precise control over generation. Extensive experiments demonstrate that significantly outperforms existing baselines,achieving state-of-the-art performance in both realism and diversity.
@article{arxiv.2605.02439,
title = {Anomaly-Preference Image Generation},
author = {Fuyun Wang and Yuanzhi Wang and Xu Guo and Sujia Huang and Tong Zhang and Dan Wang and Hui Yan and Xin Liu and Zhen Cui},
journal= {arXiv preprint arXiv:2605.02439},
year = {2026}
}