PathGuide：基于在线策略传输对齐的动态无分类器引导
PathGuide: Dynamic Classifier-Free Guidance via On-Policy Transport Alignment
浏览论文内容
中文总结 AI 辅助
PathGuide将标量CFG选择转化为在线策略传输问题，通过推导的选择准则实现动态最优引导尺度，在低分辨率图像等任务中提升了路径对齐度与样本保真度。
中文摘要 AI 辅助
尽管现代生成模型在复杂数据建模方面表现出色，但条件生成中精确的推理时控制仍是关键挑战。无分类器引导（CFG）是实现此类控制的主要机制，不过它通常被视为静态调优参数。然而在基于流的模型中，引导尺度会从根本上决定速度场和生成的概率路径，因此引导选择是一个动态路径优化问题。我们提出PathGuide框架，将标量CFG选择重新表述为在线策略传输问题。利用连续性方程的弱形式，我们推导了具有直接路径正确性解释的选择准则：我们证明，若引导场沿生成的展开过程与精确条件场弱等价，则采样器的路径与目标条件律一致。对于标量CFG，该准则产生严格的二次局部目标，每个求解器区间都有高效的闭式选择器。PathGuide可在生成过程中在线计算最优引导尺度，或离线拟合为可复用的分段常数调度。我们在低分辨率图像流形及各类连续时间流构造的受控设置中验证了该方法，结果表明，与固定引导尺度及最先进的自适应引导基线相比，这种基于传输的选择器提升了路径对齐度和样本保真度。
英文摘要
While modern generative models excel at modeling complex data, precise inference-time control in conditional generation remains a critical challenge. Classifier-free guidance (CFG) is a primary mechanism for such control, yet it is typically treated as a static tuning parameter. In flow-based models, however, the guidance scale fundamentally dictates the velocity field and the resulting probability path, making guidance selection a dynamic path-optimization problem. We introduce PathGuide, a framework that reformulates scalar CFG selection as an on-policy transport problem. Leveraging the weak form of the continuity equation, we derive a selection criterion with a direct path-correctness interpretation: we prove that if the guided field is weakly equivalent to the exact conditional field along the generated rollout, the sampler's path coincides with the target conditional law. For scalar CFG, this criterion yields a strictly quadratic local objective with an efficient, closed-form selector for each solver interval. PathGuide enables optimal guidance scales to be computed and used online during generation or fitted offline as a reusable piecewise-constant schedule. We validate our method on low-resolution image manifolds and controlled settings across various continuous-time flow constructions, demonstrating that this transport-based selector improves path alignment and sample fidelity over both fixed and state-of-the-art adaptive guidance baselines.
发表机构
- Technion - Israel Institute of Technology（以色列理工学院）
机构由 AI 辅助整理，请以论文原文为准。
