CORTIS combines Fisher-information masking and orthogonal projection to enable sequential speaker unlearning in ZS-TTS without access to prior unlearned data while preserving forgetting.
Distill, for- get, repeat: A framework for continual unlearning in text-to-image diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Continual Speaker Identity Unlearning with Minimal Interference
CORTIS combines Fisher-information masking and orthogonal projection to enable sequential speaker unlearning in ZS-TTS without access to prior unlearned data while preserving forgetting.