CATA enables persistent continual unlearning in VLMs by sign-aware aggregation of unlearning task vectors to suppress conflicts that could revive forgotten knowledge.
Erm-ktp: Knowledge-level machine unlearning via knowledge transfer,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ICED performs interpretable concept-level unlearning in VLMs by constructing a concept vocabulary via MLLM and decomposing visual representations for targeted optimization.
citing papers explorer
-
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
CATA enables persistent continual unlearning in VLMs by sign-aware aggregation of unlearning task vectors to suppress conflicts that could revive forgotten knowledge.
-
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
ICED performs interpretable concept-level unlearning in VLMs by constructing a concept vocabulary via MLLM and decomposing visual representations for targeted optimization.