Author

Zi-Niu Li

h-index 11 View on Semantic Scholar

We have 2 of 35 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 Preprint Oct 2026

HuatuoGPT-3: RL-Only Domain Adaptation from Base Models

One-stage Policy Optimization (OnePO), which treats teacher outputs as transient guidance for policy improvement, is proposed, which combines Adaptive Objective Evolution to strengthen learning on informative low-probability teacher tokens and Teacher Retirement to discard teacher outputs once the current policy can su...

Junying Chen, Xin-Yuan Xie, Zi-Niu Li et al. · 0 citations

#artificial intelligence Preprint Aug 2026

When Do Larger Batches Help Scale LLM Reinforcement Learning?

A larger-batch configuration reduces time-to-target only when its throughput gain exceeds its samples-to-target penalty, and a larger-batch configuration reduces time-to-target only when its throughput gain exceeds its samples-to-target penalty.

Zi-Niu Li, Jinbo Wang, Guan-Hua Huang et al. · 0 citations