作者位次 #3/9ICML 2026Poster· Deep Learning / Large Language Models
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
Haolong Qian · Xianliang Yang · Ma yinuo · Lirong Che · Feng Lu · Ye Guo · Lei Song · Jiang Bian · Chun Yuan