PPL
Xu Yang
Papers (6)
XPERT: Expert Knowledge Transfer for Effective Training of Language ModelsChain-based Distillation for Effective Initialization of Variable-Sized Small Language ModelsUnderstanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation TransitionsRethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-TrainingLearngene Search Across Multiple Datasets for Building Variable-Sized ModelsCorrect Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards