Diffusion models require new generalization frameworks because memorization and novel generation are incompatible, so research should focus on what models learn before memorization begins.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.
citing papers explorer
-
Understanding diffusion models requires rethinking (again) generalization
Diffusion models require new generalization frameworks because memorization and novel generation are incompatible, so research should focus on what models learn before memorization begins.
-
On the Power of Foundation Models
Category theory proves prompt-based learning on perfect foundation models works only for representable tasks, fine-tuning solves tasks in the pretext category, and models can represent unseen target-category objects using source-category structure.