OOD泛化作为分岔问题

中文摘要 AI 辅助

系统性的分布外（OOD）生成仍然是连续时间生成模型的关键瓶颈。虽然标准的联合分类器无关引导（CFG）通常无法合成未见过的概念组合，但精确分解评分能够稳健地泛化，代价是严重的计算开销。在这项工作中，我们揭示了组合绑定并非一个均匀过程，而是一个高度局部的相变。我们识别出语义分岔窗口——即联合向量场与分解向量场有意义地发散的确切时间间隔。利用这一动态，我们提出了手术引导（surgical guidance），一种混合采样策略，将精确的多遍评分严格限制在该关键窗口内。在OOD双数字MNIST测试平台上，手术引导以极低的推理成本实现了最先进的组合保真度，通过在扩散轨迹的前15%进行干预，相对于联合基线，成对准确率绝对提升了5.3%。此外，我们的实证分析揭示了一个基本的拓扑分界：扩散模型（SDEs）在峰值噪声处立即强制概念解析，而条件流匹配（ODEs）将结构绑定延迟到中间特征出现之后，为加速大规模生成解码建立了新的时间框架。

英文摘要

Systematic out-of-distribution (OOD) generation remains a critical bottleneck for continuous-time generative models. While standard joint classifier-free guidance (CFG) routinely fails to synthesize unobserved concept combinations, exact decomposed scoring generalizes robustly at the cost of severe computational overhead. In this work, we reveal that compositional binding is not a uniform process but a highly localized phase transition. We identify the semantic bifurcation window - the precise temporal interval where joint and decomposed vector fields meaningfully diverge. Exploiting this dynamic, we propose surgical guidance, a hybrid sampling strategy that restricts exact multi-pass scoring strictly to this critical window. On an OOD bi-digit MNIST testbed, surgical guidance achieves state-of-the-art compositional fidelity at a fraction of the inference cost, yielding a +5.3% absolute improvement in pairwise accuracy over the joint baseline by intervening during just the first 15% of the diffusion trajectory. Furthermore, our empirical analysis uncovers a fundamental topological divide: diffusion models (SDEs) force conceptual resolution immediately at peak noise, whereas Conditional Flow Matching (ODEs) delays structural binding until intermediate features emerge, establishing a new temporal framework for accelerating large-scale generative decoding.

发表机构

• The University of Danang - Vietnam-Korea University of Information and Communication Technology（岘港大学-越南-韩国信息通信技术大学）

机构由 AI 辅助整理，请以论文原文为准。