3 papers
cs.AI2026
Scaling Domain Data Repetition in LLM Pretraining
Jingwei Li, Xinran Gu, Rui Dai +5
As large language models scale, their training-token budgets must also increase to maintain an appropriate tokens-per-parameter ratio (\(\mathrm{TPP}\)). However, high-quality doma…
cs.LG2026
Capacity-Aware Mixture Law Enables Efficient LLM Data Optimization
Jingwei Li, Xinran Gu, Jingzhao Zhang
A data mixture refers to how different data sources are combined to train large language models, and selecting an effective mixture is crucial for optimal downstream performance. E…
cs.LG2025
Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
Xinran Gu, Kaifeng Lyu, Jiazheng Li +1
Large Language Models (LLMs) are typically trained on data mixtures: most data come from web scrapes, while a small portion is curated from high-quality sources with dense domain-s…