vix.ing · top · new · best · stats · spec

Duan, Zhenyu

  1. Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
    2025/03/13 by Wen, Liang, Cai, Yunke, Xiao, Fenrui +11 · 110 citations
    #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)