ELUDe reorganizes information flow in pretrained vision models to create monosemantic features while guaranteeing identical model outputs and no accuracy loss, without training or labels.
Title resolution pending
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
-
Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance
ELUDe reorganizes information flow in pretrained vision models to create monosemantic features while guaranteeing identical model outputs and no accuracy loss, without training or labels.