🧑‍🔬 Qiying Yu

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. DAPO: An Open-Source LLM Reinforcement Learning System at Scale (2025 · 668 citations)
   Recent reasoning LLMs owe much of their strength to large-scale reinforcement learning, but their reports leave out the recipe, so outside groups struggle to match their results.
2. VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks (2025 · 68 citations)
   Most RL work on long chain-of-thought reasoning uses critic-free methods such as GRPO and DAPO. These skip the value model and estimate advantages from group rewards. ByteDance Seed's VAPO argues that a learned value model has more potential, because it gives per-token credit assignment and lower-variance estimates…

🤝 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

• Ruofei Zhu ×2
• Tiantian Fan ×2
• Xiaochen Zuo ×2
• Yu Yue ×2
• Yufeng Yuan ×2
• Chengyi Wang
• Haibin Lin
• Jiaze Chen
• Lingjun Liu
• Wenyuan Xu
• Xiangpeng Wei
• Xin Liu

🔗 Cited by

Papers of our library cite their works 719 times (of the 149,439 papers whose bibliographies we read); 233 citing papers with a page here →.

Updated 2 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/qiying-yu/