Author

Zhenghao Xu

2 papers indexed here

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 Sep 2026

Training LLM Judges from Language Feedback via Position-Selective Self-Distillation

We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and how it weighs them. The dominant approach, outcome-supervised RL (e.g., GRPO), credits every token in the rollout with a single scalar determ...

Ilgee Hong, Chang-Long Yu, Zhenghao Xu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Rufus-Air: An Open LLM Post-Training Recipe

Rufus-Air is an open and reproducible post-training recipe on GLM-4.5-Air-Base (106B-A12B), organized as a serial pipeline of eight stages: SFT, Reasoning RL, Coding RL, Instruction-Following RL, General Agent, Coding Agent, Search Agent, and RLHF. We document the data, reward design, infrastructure, stage order, and s...

Chia-yuan Chang, Ren-Yuan Cheng, Rui Feng et al. · 0 citations