Research2026-04-30
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Source: Arxiv CS.AI
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 Diffusion Models (UDDMs) fundamentally behave as...
arxivpapersimage-generation