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

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning arXiv:2601.22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners often need group-level answers (e.g., artistic styles or object classes). Group-wise attribution is counterfactual: how would a model's behavior on a generated sample c