注意力，能否告诉我你的决定？定位扩散模型中的生成性选择
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
用基于探针的属性可分性定位扩散模型中隐式决策发生的层，并据此只对少量自注意力层做定向干预；这套「先定位再干预」的流程可直接迁移到视觉生成中的属性去偏、概念编辑与生成可控性研究。
原文依据 we introduce a probing-based localization technique to identify the layers with the highest attribute separability for concepts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到图像扩散模型展现出卓越的生成能力，但其内部运作仍不透明，尤其是在处理描述不充分的提示词时。在此类情形下，模型必须做出隐式决策，以生成文本中未明确指定的细节。本文研究如下假设：这一决策过程并非弥散分布，而是在模型架构中计算上局部化的。现有定位技术聚焦于与提示词相关的干预，但我们注意到这类显式条件可能与隐式决策并不相同。因此，我们引入一种基于探针的定位技术，以识别对概念具有最高属性可分性的层。研究结果表明，歧义概念的消解主要由自注意力层主导，从而将这些层确定为最有效的干预点。基于这一发现，我们提出 ICM（隐式选择修正）——一种精确引导方法，仅对少量层施加定向干预。大量实验证实，相较于现有最优方法，对这些特定自注意力层进行干预可获得更优的去偏性能，并最大限度减少精度较低的方法常见的伪影。
英文原文摘要 1317 字符
Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling prompts that are not fully descriptive. In such scenarios, models must make implicit decisions to generate details not explicitly specified in the text. This work investigates the hypothesis that this decision-making process is not diffuse but is computationally localized within the model's architecture. While existing localization techniques focus on prompt-related interventions, we notice that such explicit conditioning may differ from implicit decisions. Therefore, we introduce a probing-based localization technique to identify the layers with the highest attribute separability for concepts. Our findings indicate that the resolution of ambiguous concepts is governed principally by self-attention layers, identifying them as the most effective point for intervention. Based on this discovery, we propose ICM (Implicit Choice-Modification) - a precise steering method that applies targeted interventions to a small subset of layers. Extensive experiments confirm that intervening on these specific self-attention layers yields superior debiasing performance compared to existing state-of-the-art methods, minimizing artifacts common to less precise approaches.