Author

Itai Zehavi

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders

This work introduces SCALPEL, a contrastive sparse autoencoder designed to learn more selective forget features and shows theoretically that contrastive training promotes target-selective features and that the selection score controls expected background knowledge perturbation.

Itai Zehavi, Fanny Jourdan, Ulrich Aivodji · 0 citations