发表机构
UT Austin（德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究提出带符号整流流（Signed RF），通过推广整流流，基于带符号测度构建生成模型，能将概率集中在正区域并排除负区域。分析其连续性方程并给出解释，推动实用算法，在多应用中提升性能，改进了保真度 - 多样性权衡等。
AI 中文摘要
我们引入带符号整流流（Signed RF），它是整流流的一种推广，目标是带符号测度$\pi^{sign}=(1 + \alpha)\pi^+ - \alpha\pi^-$，其中$\alpha>0$，$\pi^+$是要促进的分布，$\pi^-$是要抑制的分布。虽从带符号测度直接采样未明确定义，但Signed RF诱导出一个有效的生成过程，将概率集中在带符号测度为正的区域，同时可证明排除由其负分量主导的区域。它为将负信息和排除约束纳入生成建模提供了一个有原则的框架。我们分析了Signed RF背后的带符号连续性方程，并用带电粒子解释说明了负质量如何形成排除障碍。该理论进一步推动了实用的自适应引导算法。在多个应用中，Signed RF改善了ImageNet上的保真度 - 多样性权衡，在抗记忆实验中降低了最近邻相似度，并在保持CLIP和美学分数的同时减少了Stable Diffusion 3.5中对抗性提示引起的裸露。
英文摘要
We introduce Signed Rectified Flow (Signed RF), a generalization of Rectified Flow that targets the signed measure $π^{sign} = (1+α)π^+ - απ^-$, where $α>0$, $π^+$ is the distribution to promote, and $π^-$ is the distribution to suppress. Although direct sampling from a signed measure is not well-defined, Signed RF induces a valid generative process that concentrates probability in regions where the signed measure is positive while provably excluding regions dominated by its negative component. It therefore provides a principled framework for incorporating negative information and exclusion constraints into generative modeling. We analyze the signed continuity equation underlying Signed RF and use a charged-particle interpretation to explain how negative mass forms exclusion barriers. This theory further motivates practical adaptive guidance algorithms. Across several applications, Signed RF improves the fidelity-diversity trade-off on ImageNet, reduces nearest-neighbor similarity in anti-memorization experiments, and reduces nudity induced by adversarial prompts in Stable Diffusion 3.5 while preserving CLIP and aesthetic scores.
