Author

Tianrun Yu

Observed name: Yu, Tianrun

Institution: Brigham Young University

Observed institution: Brigham Young University

OpenAlex ID: A5127923048

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

2026 · Yu, Tianrun, Zhao, Kaixiang, et al. · arXiv (Cornell University)

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

2026 · Yang, Yuxiao, Yu, Tianrun, et al. · arXiv (Cornell University)

Provable and Practical In-Context Policy Optimization for Self-Improvement

2026 · Yu, Tianrun, Yang, Yuxiao, et al. · arXiv (Cornell University)

Works count: 3

Citation count:

H-index:

I10-index: