GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning 文章

ArXiv CS.AI2026-06-02NEWSen作者: Naoki Murata, Yuhta Takida, Chieh-Hsin Lai, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
查看原文 →
关系图谱

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning · 相关技术

相关技术

Leave-One-Group-OutMachine unlearningdiffusion modelsGUDALeave-One-Group-Out (LOGO) retrainingvision generative models