English(EN) Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

新的MUCS方法增强了扩散模型的数据归因能力

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-18 06:52

研究人员开发了一种名为镜像遗忘和噪声一致偏倚（MUCS）的新方法，以改进扩散模型的训练数据归因（TDA）。该技术旨在使生成模型的可解释性更加可靠和稳健，解决了当前阻碍实际应用的一些限制。MUCS涉及微调一个辅助模型，并使用一致的噪声样本测量其相对于原始模型的偏倚，在多个数据集上表现显著优于现有方法。 AI

影响提高了扩散模型的可解释性和稳健性，可能促进更广泛的应用和新的下游应用。

排序理由发布了一篇关于扩散模型新方法的学术论文。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv stat.ML TIER_1 English(EN) · Joan Serr\`a, Dipam Goswami, Fabio Morreale, Wei-Hsiang Liao, Yuki Mitsufuji · 2026-05-19 04:00

Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

arXiv:2605.17938v1 Announce Type: cross Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in re…
arXiv stat.ML TIER_1 English(EN) · Yuki Mitsufuji · 2026-05-18 06:52

Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliability and robustness, preventing their adoption in real-world setups. In this paper, we take a decisive…

报道来源 [2]

Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew

相关实体

相关话题