TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.
ICLR , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
SwordBench benchmarks steering methods for concept removal in vision models and shows that linear SVMs achieve strong separability and orthogonality but incur collateral damage, while sparse autoencoders often perform better and no method reaches perfect steering even in simple cases.
citing papers explorer
-
TILT: Target-induced loss tilting under covariate shift
TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.
-
SwordBench: Evaluating Orthogonality of Steering Image Representations
SwordBench benchmarks steering methods for concept removal in vision models and shows that linear SVMs achieve strong separability and orthogonality but incur collateral damage, while sparse autoencoders often perform better and no method reaches perfect steering even in simple cases.