ICLR Poster "memorization quantification" Papers
2 papers found
Captured by Captions: On Memorization and its Mitigation in CLIP Models
Wenhao Wang, Adam Dziedzic, Grace Kim et al.
ICLR 2025posterarXiv:2502.07830
4
citations
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
Michael Aerni, Javier Rando, Edoardo Debenedetti et al.
ICLR 2025posterarXiv:2411.10242
13
citations