🧑‍🔬 Kun Gai

🏛️ Affiliations

🏢KuaishouBeijing · China2023–2026 · 82 paperscurrent🎓Klaipėda UniversityKlaipėda · Lithuania2026 · 2 paperscurrent🎓Peking UniversityBeijing · China2026 · 1 papercurrent🏢Shanghai Dramatic Arts CentreXuhui · China2026 · 1 papercurrent🏥Shanghai Xuhui Central HospitalShanghai · China2026 · 1 papercurrent🏢Alibaba GroupHangzhou · China2012–2025 · 37 papers🎓Tsinghua UniversityBeijing · China2008–2024 · 8 papers🔬State Key Laboratory of Intelligent Technology and SystemsBeijing · China2009–2011 · 6 papers🎓Jinan UniversityGuangzhou · China2018 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed.

🧭 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. CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning (2026 · 7 citations)
   The paper tackles unstable policy entropy when large language models are trained with RL for reasoning. PPO-style methods, including GRPO and DAPO, clip the importance sampling ratio, and this silently drops gradients from low-probability tokens. The authors split tokens by advantage sign and probability. They argue…
2. Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning (2026 · 1 citation)
   LLM post-training with reinforcement learning is usually off-policy, so updates use samples from older policies.

All works

6 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Deep Interest Evolution Network for Click-Through Rate Prediction ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetGuorui Zhou et al.2019 · 1,102 citations
2. Leanabell-Prover: Posttraining Scaling in Formal Reasoning ↗arXiv:2504.06122 · no summary yetJingyuan Zhang et al.2025 · 21 citations
3. CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Zhenpeng Su, Leiyu Pan, Minxuan Lv, et al.2026 · 7 citations
4. Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement LearningFindings of the Association for Computational LinguisticsZhenpeng Su, Leiyu Pan, Minxuan Lv, et al.2026 · 1 citation
5. DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetHongzhi Zhang et al.2026
6. Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetZhiyang Zhang et al.2026

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Guorui Zhou ×2
• Leiyu Pan ×2
• Minxuan Lv ×2
• Wenping Hu ×2
• Yuntao Li ×2
• Zhenpeng Su ×2
• Fuzheng Zhang
• Ruiming Tang
• Tiehua Mei

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×2: ACL 2026
• Findings of the Association for Computational Linguistics: ACL 2026 ×2
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the AAAI Conference on Artificial Intelligence

🔗 Cited by

Papers of our library cite their works 73 times (of the 149,439 papers whose bibliographies we read); 9 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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