**摘要**
Standard diffusion models typically use a single time-homogeneous Gaussian terminal distribution as the reference law for generation. While this choice is analytically convenient and empirically powerful, it provides little explicit structure for data concentrated near low-dimensional manifolds, where different regions of the data distribution may correspond to distinct local geometric or semantic
👤 作者: Danqi Zhuang, Jisui Huang, Xiaoyue Xi, Andrew Kiggins, Xiaojie Wang, Ke Chen, Yue Wu

---
🔗 **[PTL扩散：具有周期性终端规律的歧管感知扩散](https://arxiv.org/abs/2606.09816v1)**

> PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-09 14:01