2 papers
stat.ME2025
Gold after Randomized Sand: Model-X Split Knockoffs for Controlled Transformation Selection
Yang Cao, Hangyu Lin, Xinwei Sun +1
Controlling the False Discovery Rate (FDR) is critical for reproducible variable selection, especially given the prevalence of complex predictive modeling. The recent Split Knockof…
cs.LG2024
Mitigating the Alignment Tax of RLHF
Yong Lin, Hangyu Lin, Wei Xiong +14
LLMs acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, w…