作者位次 #4/9ICML 2026Poster· Deep Learning / Large Language Models
Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
Shengrui Li · Fei zhao · Kaiyan Zhao · Jieying Ye · Haifeng Liu · Fangcheng Shi · Zheyong Xie · Yao Hu · Shaosheng Cao