Author

Le Sun

h-index 31 View on Semantic Scholar

We have 2 of 182 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.

#artificial intelligence Mar 2026

P^2O: Joint Policy and Prompt Optimization

Joint Policy and Prompt Optimization (P O) is introduced to mitigate advantage collapse by alternating continuous policy updates with discrete prompt evolution, providing a self-reinforcing framework that facilitates more effective LLM alignment.

Xinyu Lu, Kaiqi Zhang, Jing-Li Yang et al. · arXiv.org · 2 citations

Preprint Jul 2026

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

A short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes, treats the surviving prefix as each rollout's effective length, and allocates future rollout budgets to the effective lengths the policy can currently use is proposed.

Qingyu Zhang, Qianhao Yuan, Hongyu Lin et al. · 5 citations