Uniform-based discrete diffusion models behave as associative memories that retrieve unseen data, with a dataset-size-driven memorization-to-generalization transition detectable via conditional entropy of token predictions.
The rules-and-facts model for simultaneous generalization and memorization in neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Uniform-based discrete diffusion models behave as associative memories that retrieve unseen data, with a dataset-size-driven memorization-to-generalization transition detectable via conditional entropy of token predictions.