作者位次 #4/5ACL 2026Poster· Natural Language Processing
Revisiting Model Interpolation for Efficient Reasoning
Taiqiang Wu · Runming Yang · Tao Liu · Jiahao Wang · Ngai Wong
摘要
Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging method that interpolates two weights directly. Particularly, we observe that model interpolation follows a three-stage...