👋 Hi, I’m Yantao Liu — currently a Senior Algorithm Engineer at Qwen.
My work focuses on Reward Modeling and Reinforcement Learning training of LLMs.

👉 For my full list of publications, please refer to my Google Scholar profile.

• RM-Bench — A benchmark that tests reward models on subtle content differences and style bias resistance to better align language models.
• PairJudge-RM — A pairwise reward model using knockout tournaments to improve Best-of-N sampling for LLMs.
• HelpSteer3 — An open-source dataset for training models to generate more helpful responses to user prompts.

If you’re interested in reward modeling or any of my projects, feel free to email me personal email!

• M.S. Student
  University of the Chinese Academy of Sciences
  2022 – 2025

• B.S. Student
  Beijing University of Posts and Telecommunications
  2018 – 2022

Thanks for visiting my page!