通过低频空间进化搜索，高效实现图像生成的奖励对齐。
Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation
- 在低频子空间中进行无梯度进化搜索，避免无效高频率扰动。
- 相比基线方法，在相同计算成本下生成质量显著提升。
- 适合需要高效推理调优的图像生成应用，如可控生成与风格迁移。
推理时缩放提供了一种灵活的范式，可在不更新参数的情况下将视觉生成模型对齐到下游目标。然而，现有方法优化高维初始噪声时效率极低，因为许多搜索方向对最终生成结果影响微乎其微。我们发现这种低效性与生成动态中的谱偏差密切相关：模型对高频扰动的敏感度随频率升高迅速下降。基于此洞察，我们提出谱演化搜索（Spectral Evolution Search, SES），一种可即插即用的初始噪声优化框架，通过在低频子空间内执行无梯度进化搜索实现高效优化。理论上，我们从扰动传播动力学推导出谱缩放预测（Spectral Scaling Prediction），解释了不同频率扰动影响的系统性差异。大量实验表明，SES 显著提升了生成质量与计算成本之间的帕累托前沿，在同等预算下持续优于强基线。
原文摘要 · Abstract (English)
Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe inefficiency, as many search directions exert negligible influence on the final generation. We show that this inefficiency is closely related to a spectral bias in generative dynamics: model sensitivity to initial perturbations diminishes rapidly as frequency increases. Building on this insight, we propose Spectral Evolution Search (SES), a plug-and-play framework for initial noise optimization that executes gradient-free evolutionary search within a low-frequency subspace. Theoretically, we derive the Spectral Scaling Prediction from perturbation propagation dynamics, which explains the systematic differences in the impact of perturbations across frequencies. Extensive experiments demonstrate that SES significantly advances the Pareto frontier of generation quality versus computational cost, consistently outperforming strong baselines under equivalent budgets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。