SAAD adaptively weights adversarial training samples by their transferability to the teacher, yielding higher AutoAttack robustness than prior distillation methods on CIFAR and Tiny-ImageNet without extra compute.
Rethinking soft labels for knowledge distillation: A bias-variance tradeoff perspective
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Leakage-aware distillation transfers at least 90% of tabular foundation model AUC to lightweight students across 19 health datasets, with 26x CPU speedup and preserved calibration/fairness.
LLM confidence for social science text measurements is poorly calibrated across models, and a soft-label distillation pipeline reduces expected calibration error by 43% and Brier score by 34%.
citing papers explorer
-
Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation
SAAD adaptively weights adversarial training samples by their transferability to the teacher, yielding higher AutoAttack robustness than prior distillation methods on CIFAR and Tiny-ImageNet without extra compute.
-
Distilling Tabular Foundation Models for Structured Health Data
Leakage-aware distillation transfers at least 90% of tabular foundation model AUC to lightweight students across 19 health datasets, with 26x CPU speedup and preserved calibration/fairness.
-
Assessing and Mitigating Miscalibration in LLM-Based Social Science Measurement
LLM confidence for social science text measurements is poorly calibrated across models, and a soft-label distillation pipeline reduces expected calibration error by 43% and Brier score by 34%.