2 papers
cs.AI2026
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models
Leonardo Santiago Benitez Pereira, Marcos Escudero Viñolo, Luis Herranz Arribas
Machine unlearning studies the removal of knowledge from an AI model, making the system forget a concept it previously learned. Despite rapid progress in generative machine unlearn…
cs.CV2026
SPARE: Self-distillation for PARameter-Efficient Removal
Natnael Mola, Leonardo S. B. Pereira, Carolina R. Kelsch +2
Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data pr…