cs.AI, cs.CL, cs.LG

Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data

arXiv:2604.26841v1 Announce Type: cross
Abstract: When do language diffusion models memorize their training data, and how to quantitatively assess their true generative regime? We address these questions by showing that Uniform-based Discrete Diffusio…