Huayu Chen
Huayu Chen has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Reasoning; often with Ganqu Cui, Hao Peng, Lifan Yuan.
OpenAlex · ORCID · h-index 23 · 88 works · 1,773 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 332 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #6974
Affiliations
Fields, topics and concepts
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works
🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workReasoning · 1 work
Works by year
2020s
Papers
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models (2025 · 101 citations)
Reinforcement learning with verifiable rewards is now a main way to improve LLM reasoning, but scaling it hits a recurring problem. Without explicit regularization, policy entropy falls to almost zero within the first training steps. The model becomes overconfident, stops exploring and its validation accuracy stalls. - Free Process Rewards without Process Labels (2024 · 58 citations)
Process reward models (PRMs) score each step of a reasoning chain and often beat outcome reward models (ORMs), but they need step-level labels.
All works
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language ModelsarXiv:2505.22617Ganqu Cui, Yuchen Zhang, Jiacheng Chen, et al.2025 · 101 citations
- Free Process Rewards without Process LabelsarXiv:2412.01981Lifan Yuan, Wendi Li, Huayu Chen, et al.2024 · 58 citations
- DiffusionNFT: Online Diffusion Reinforcement with Forward Process ↗arXiv (Cornell University) · no summary yetKaiwen Zheng et al.2025 · 26 citations
Co-authors here
- Ganqu Cui ×2
- Hao Peng ×2
- Lifan Yuan ×2
- Zhiyuan Liu ×2
- Bowen Zhou
- Haozhan Li
- Jiacheng Chen
- Kaiyan Zhang
- Ning Ding
- Weize Chen
- Wendi Li
- Yuchen Fan
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/huayu-chen/