1 citations · 1 across the 4 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CV2025
SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
Enrico Cassano, Riccardo Renzulli, Marco Nurisso +3
Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computatio…
cs.LG2025
Bound by semanticity: universal laws governing the generalization-identification tradeoff
Marco Nurisso, Jesseba Fernando, Raj Deshpande +9
Intelligent systems must deploy internal representations that are simultaneously structured -- to support broad generalization -- and selective -- to preserve input identity. We ex…