← 研踪 PaperTrailarXiv:2611.03764 · v1
The role of injected noise in diffusion model generalization
首次提交 2026-11-02 22:51
版本更新 2026-11-02 22:51
雷达观测 2026-11-04 23:41
摘要
Diffusion models trained on distinct datasets can produce highly similar samples when prompted with the same noise input, suggesting that they learn a generalized data distribution. We investigate the role of noise injected during the sampling process, and show that it plays an important role in making or breaking this strong generalization effect. Based on this finding we investigate the robustness of sample similarity to changes in the injected noise, and find that its impact is largest in the sampling regime where broad structure already exists but the precise identity of the sample is not yet determined.
作者备注：10 pages, 11 figures, published at the NeurIPS 2026 Workshop: 2nd Workshop on Principles of Generative Modeling (PriGM)
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-02 22:51 · 最新观测版本
The role of injected noise in diffusion model generalization
Diffusion models trained on distinct datasets can produce highly similar samples when prompted with the same noise input, suggesting that they learn a generalized data distribution. We investigate the role of noise injected during the sampling process, and show that it plays an important role in making or breaking this strong generalization effect. Based on this finding we investigate the robustness of sample similarity to changes in the injected noise, and find that its impact is largest in the sampling regime where broad structure already exists but the precise identity of the sample is not yet determined.
查看此版本解读 →查看此版本原文 ↗