Preprint
Aug 2026
DualOPSD: Adaptive Privileged Teachers for On-Policy Self-Distillation
DualOPSD, an asymmetric alternating framework that adapts both policies, reduces truncation across all three scales, and makes later supervision responsive to the learner and does not require another rollout.
Yu-Tong Chen, Guangfu Guo, Zhi-Chao Xu et al.
· 0 citations