conftrace_

continual unlearning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

generative identity unlearning (1) relearning attack (1) refusal generation (1) adversarial gradient (1) concept decomposition (1) privacy protection (1) vision-language model (1) mixture of expert (1)

Papers

ROVER: Robust Generative Continual Identity Unlearning Against Relearning Attacks AAAI 2026 Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models CVPR 2026