Losing dimensions: Geometric memorization in generative diffusion

arXiv:2410.08727v2 Announce Type: replace-cross Abstract: Diffusion models power leading generative AI, but when and how they memorize training data, especially on low-dimensional manifolds, remains unclear. We find memorization emerges gradually, not abruptly: as data become ...

🔗 Read more: https://arxiv.org/abs/2410.08727

#News #Energy #Psychology #Policy #Biology #Academic