TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.
Journal of Machine Learning Research , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3roles
method 1polarities
use method 1representative citing papers
CFM-SD treats physical simulators as do-operators to identify d-variable causal structures with O(d) interventions and reduces bias in molecular and battery prediction tasks.
A new battery of 30 cognitive tasks demonstrates that process-level behavioral features distinguish humans from frontier AI agents better than performance metrics (mean AUC 0.88), with process-specific fine-tuning improving mimicry but limited cross-task transfer.
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.
-
Physical Simulators as Do-Operators: Causal Discovery under Latent Confounders for AI-for-Science
CFM-SD treats physical simulators as do-operators to identify d-variable causal structures with O(d) interventions and reduces bias in molecular and battery prediction tasks.
-
Process Matters more than Output for Distinguishing Humans from Machines
A new battery of 30 cognitive tasks demonstrates that process-level behavioral features distinguish humans from frontier AI agents better than performance metrics (mean AUC 0.88), with process-specific fine-tuning improving mimicry but limited cross-task transfer.