Wang, Jiakang

1. Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
   2025/07/21 by Wang, Jiakang, Liu, Runze, Zhang, Fuzheng +2 · 17 citations
   #Computation and Language (cs.CL) #FOS: Computer and information sciences
2. When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL
   2025/10/07 by Runze Liu, Wang, Jiakang, Cai, Qingpeng +12 · 2 citations
   Decision Sciences · Mathematics · #Simulation Techniques and Applications #Statistical Methods and Inference