collaborators

6 papers

cs.LG2026

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity

Fengyuan Liu, Yongliang Miao, Zirui He +3

Reward models trained from pairwise preferences often exploit superficial shortcut cues rather than learning true response quality. We propose DynaCF, a dynamic reweighting framewo…

stat.ML2026

LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetry

Xunye Tian, Zhijian Zhou, Liuhua Peng +1

Data-adaptive two-sample testing assesses if two samples come from the same distribution, using a discrepancy learned from the data (e.g., via kernel-based feature representations)…

cs.LG2026

Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs

Ke Li, Chongzhe Zhang, Zifan Zeng +3

Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted conf…

stat.ML2026

Learning Representations for Independence Testing

Nathaniel Xu, Feng Liu, Danica J. Sutherland

Many tools exist to detect dependence between random variables, a core question across a wide range of machine learning, statistical, and scientific endeavors. Although several sta…

cs.LG2026

Unlearning Evaluation through Subset Statistical Independence

Chenhao Zhang, Muxing Li, Feng Liu +2

Evaluating machine unlearning remains challenging, as existing methods typically require retraining reference models or performing membership inference attacks, both of which rely…

cs.LG2025

DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing

Zhijian Zhou, Xunye Tian, Liuhua Peng +4

To adapt kernel two-sample and independence testing to complex structured data, aggregation of multiple kernels is frequently employed to boost testing power compared to single-ker…