注意力频率调制：无训练的扩散交叉注意力频谱调制
Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention
AI总结：
本文提出AFM，通过频域调整交叉注意力logits，实现无训练的注意力频谱控制，实验证明能有效编辑图像内容并保持语义一致性。
摘要：
交叉注意力是文本条件化潜在扩散模型的主要接口，但其逐步多分辨率动态特性未被充分表征，限制了无训练控制。本文将扩散交叉注意力视为潜在网格上的时空信号，通过将token-softmax权重总结为token-无关浓度图，并跟踪去噪过程中token的径向分箱傅里叶功率。在不同提示和种子下，编码器交叉注意力表现出一致的粗到细频谱进展，产生稳定的时频指纹。基于此结构，本文引入注意力频率调制（AFM），一种插件式推理时间干预，通过傅里叶域调整token级pre-softmax交叉注意力logits：低频和高频带根据进度对齐的计划重新加权，并可通过token分配熵自适应门控。AFM提供连续的手段，无需重新训练、提示编辑或参数更新，即可偏移token竞争模式的空间尺度。在Stable Diffusion上的实验表明，AFM可靠地重新分配注意力频谱，产生显著的视觉编辑，同时保持语义一致性。最后发现熵主要作为同一频率基编辑的自适应增益，而非独立控制轴。
英文摘要：
Cross-attention is the primary interface through which text conditions latent diffusion models, yet its step-wise multi-resolution dynamics remain under-characterized, limiting principled training-free control. We cast diffusion cross-attention as a spatiotemporal signal on the latent grid by summarizing token-softmax weights into token-agnostic concentration maps and tracking their radially binned Fourier power over denoising. Across prompts and seeds, encoder cross-attention exhibits a consistent coarse-to-fine spectral progression, yielding a stable time-frequency fingerprint of token competition. Building on this structure, we introduce Attention Frequency Modulation (AFM), a plug-and-play inference-time intervention that edits token-wise pre-softmax cross-attention logits in the Fourier domain: low- and high-frequency bands are reweighted with a progress-aligned schedule and can be adaptively gated by token-allocation entropy, before the token softmax. AFM provides a continuous handle to bias the spatial scale of token-competition patterns without retraining, prompt editing, or parameter updates. Experiments on Stable Diffusion show that AFM reliably redistributes attention spectra and produces substantial visual edits while largely preserving semantic alignment. Finally, we find that entropy mainly acts as an adaptive gain on the same frequency-based edit rather than an independent control axis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
