arXivGuhan Chen, Bohan Li, Jun Rao, Hejin Wang, Songtao Tian, Yexin Xie, Xiaojun Meng, Peng Yuan, Jiansheng Wei, Xuebo Liu, Zixiong YuThu, Nov 5, 2026, 4:55 AM PST
score 16.7
Training method fills gaps in student AI models
Original: CoRD: Coupled Rollouts Fill the Blind Spot of On-Policy Distillation
Source: arxiv.org ↗
Writing ELI5 summary…