ModalImmune enforces modality immunity in multimodal models by controlled collapse of input channels during training using adaptive regularizers and meta-optimization.
Projective fisher information for natural gradient descent.IEEE Transactions on Artificial Intelligence, 4(2):304–314, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ModalImmune: Immunity Driven Unlearning via Self Destructive Training
ModalImmune enforces modality immunity in multimodal models by controlled collapse of input channels during training using adaptive regularizers and meta-optimization.