Author

Wan Du

h-index 7 View on Semantic Scholar

We have 2 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live?

On-policy distillation (OPD) is increasingly studied as a cheaper alternative to reinforcement learning, yet it remains a form of knowledge distillation (KD) that relies on teacher supervision. We revisit OPD from the KD perspective by asking where the teacher's advantage lies along student-generated trajectories. Cont...

Yi-Ping Li, Fan Zhao, Zhi-Bo Hou et al. · 0 citations

Preprint Aug 2026

From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection

This work proposes Golden-GRPO Injection (GRIN), a three-stage self-learning framework for continual knowledge injection that substantially outperforms SFT and mixed-policy RL baselines on the harder question types while matching them on basic fact recall.

Zhibo Hou, Fan Zhao, Zhi-Yu An et al. · 0 citations