作者位次 #4/8ICLR 2026Oral
RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format
Zhehao Huang · Yuhang Liu · Baijiong Lin · Yixin Lou · Zhengbao He · Hanling Tian · Tao Li · Xiaolin Huang