Author name: Wei Yao, Wang Zhaoyang, Gengze Xu, Chen Qian, Dongrui Liu, Ziqiao Wang, Yong Liu, Yunbei Xu

arXiv:2605.05710v1 Announce Type: new
Abstract: The paradigm of Weak-to-Strong Generalization (W2SG) suggests that a pre-trained strong model can surpass its weak supervisor, yet the decisive role of pre-training remains theoretically and empirically …