1
Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
新方法追踪模型合并中的秩1子空间，为语言模型预训练提速增效。
arXiv:2605.26484v1 Announce Type: new Abstract: Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet it…