Fengze Liu

LayerMix Law: Scaling Law for Large Language Models on Quality-Weighted Mixture Data with Repetition

QUADMIX: QUALITY-DIVERSITY BALANCED DATA SELECTION FOR EFFICIENT LLM PRETRAINING

TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining

Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining