5 papers
On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models
Shuoyuan Wang, Beier Luo, Hao Zeng +5
Large reasoning models (LRMs) often suffer from overconfidence when expressing their uncertainty. Confidence-aware reinforcement learning (RL) offers a promising way to optimize ca…
Robust Conformalized Selection with Noisy Responses
Chengyao Yu, Hongxin Wei, Bingyi Jing
Conformalized selection has been widely applied to select high-quality candidates from large datasets with rigorous uncertainty quantification, such as reliable labeling, drug disc…
Anytime Safe PAC Efficient Reasoning
Chengyao Yu, Hao Zeng, Youxin Zhu +3
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks but suffer from high computational costs and latency. While selective thinking strategies im…
FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference
Chenqing Lin, Mostafa Hussien, Chengyao Yu +4
Structured pruning is a standard tool for compressing deep neural networks, but its practical performance depends on how sparsity is allocated across layers. We propose FAIR-Pruner…
A generalized e-value feature detection method with FDR control at multiple resolutions
Chengyao Yu, Ruixing Ming, Min Xiao +2
Multiple resolutions arise across a range of explanatory features due to domain-specific structures, leading to the formation of feature groups. It follows that the simultaneous de…