Guidance Breaks the Fitted Operator: A Terminal-Fitted Repair for Classifier-Free Guidance

📄 arXiv: 2607.07665v1 📥 PDF

作者: Shiheng Zhang

分类: cs.LG, math.NA

发布日期: 2026-07-08

💡 一句话要点

提出终端拟合修复方法以解决分类器无关引导的过饱和问题

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱四：生成式动作 (Generative Motion)

关键词: 分类器无关引导 扩散模型 数值分析 图像生成 深度学习

📋 核心要点

  1. 现有的分类器无关引导方法在大引导下会导致过饱和和不稳定，影响采样质量。
  2. 本文提出了一种新的修复方法，通过调整引导方向的参数，解决了CFG的发散问题。
  3. 实验结果表明，该方法在CIFAR-10和Stable Diffusion 1.5 DDIM上显著提升了采样质量，且没有额外计算成本。

📝 摘要（中文）

分类器无关引导（CFG）是增强扩散和流匹配采样器中类条件的标准方法，但在大引导下会出现过饱和和不稳定现象。本文通过渐近保持和数值分析的视角分析CFG，提出了一种修复方法，能够消除CFG的sigma_min发散问题，并在CIFAR-10和Stable Diffusion 1.5 DDIM上表现出色，成为高引导稳定器。

🔬 方法详解

问题定义：本文旨在解决分类器无关引导（CFG）在大引导下导致的过饱和和不稳定问题。现有方法通过增加步骤或限制间隔来抑制这些现象，但效果有限。

核心思路：论文的核心思路是通过分析CFG的渐近性质，提出一种替代CFG引导方向的修复方法，从而消除sigma_min发散问题。

技术框架：整体架构包括对CFG的分析、提出的修复方法以及在不同数据集上的验证。主要模块包括引导方向的调整和性能评估。

关键创新：最重要的创新点在于提出了一种一系数、零额外NFE的修复方法，替代CFG的引导方向参数，使得在小sigma情况下的引导流更为准确。

关键设计：关键设计包括对引导方向参数的重新定义，确保在引导过程中不会出现发散，同时保持与精确引导流的一阶准确性。

🖼️ 关键图片

fig_0
fig_1

📊 实验亮点

实验结果显示，该修复方法在CIFAR-10上实现了9/9的点-FID胜利，相比于传统CFG显著降低了残差放大和饱和现象。此外，在Stable Diffusion 1.5 DDIM上也表现出色，成为高引导稳定器而无需额外计算成本。

🎯 应用场景

该研究的潜在应用领域包括图像生成、计算机视觉和深度学习模型的优化。通过提高采样稳定性和质量，该方法可以在多种生成任务中发挥重要作用，推动相关技术的发展。

📄 摘要（原文）

Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules. We analyze CFG through an asymptotic-preserving, numerical-analysis lens. Building on a recent result that the deterministic DDIM step is the unique fitted operator for the unguided terminal layer, exact on the final small-sigma stretch of sampling, we show that guidance re-stiffens exactly the discriminative subspace to an anomalous exponent 1+w. DDIM is therefore no longer fitted there, and on coarse meshes its guided residual diverges as sigma_min goes to zero. We prove a guided clock barrier with three ordered step-size thresholds, and read one-step oversaturation as its endpoint: a solver artifact on the calibration model rather than the continuous guided law. The same analysis yields a one-coefficient, zero-extra-NFE repair: replace CFG's w(r-1) by r^(1+w)-r on the guidance direction. On the calibration model's discriminative crossover, this removes CFG's sigma_min-divergent blow-up and is first-order accurate against the exact guided flow as sigma_min goes to zero. On learned CIFAR-10 checkpoints, and as a cross-domain smoke test on Stable Diffusion 1.5 DDIM, it acts as a high-guidance stabilizer at no extra cost rather than a universal quality knob: it cuts residual amplification and saturation, gives 9/9 point-FID wins over CFG on the tested grid, and preserves classifier-proxy target accuracy in the hard-cell blocks. We report the limits alongside: it is not a universal image-quality win, and against a dense vanilla-CFG reference it is not a uniformly better integrator of that field.