Research

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

Single source1 source14 Oct 2026

arXiv:2605.17938v2 Announce Type: replace-cross Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2605.17938

← Back to all developments · Signals are a development reported by more than one source. See the methodology.