← back
arXivYandu Sun, Zhiyan Hou, Haokai Ma, Yuheng Jia, Junfeng Fang, Haiyun Guo, Hongyan An, weizhen wang, Jinqiao WangMon, Jun 1, 2026, 6:42 AM PDT
score 16.4

Merging AI models trained with reinforcement learning without retraining

Original: ResMerge: Residual-based Spectral Merging of Large Language Models

Source: arxiv.org

Writing ELI5 summary…