Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models
Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed +2
Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable…
cs.CV2026
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.CV2025
When Does Pruning Benefit Vision Representations?
Enrico Cassano, Riccardo Renzulli, Andrea Bragagnolo +1
Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper invest…