--- title: "Kun Gai · Peking University — author profile and papers" description: "Kun Gai, Peking University: 4 papers on Elamur Research (2026), h-index 30 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/kun-gai/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/kun-gai/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Kun Gai # Kun Gai Kun Gai has 4 papers in our library, in 2026; often with [Guorui Zhou](https://md.research.elamur.ai/free/en/authors/guorui-zhou/), [Ruiming Tang](https://md.research.elamur.ai/free/en/authors/ruiming-tang/), [Han Li](https://md.research.elamur.ai/free/en/authors/han-li/). 4 papers in our library · 2026 [OpenAlex](https://openalex.org/A5062939922) · [ORCID](https://orcid.org/0000-0002-3636-3618) · [Wikidata](https://www.wikidata.org/wiki/Q130855086) · [**h-index 30**](https://openalex.org/authors/A5062939922) · [276 works](https://openalex.org/works?filter=author.id:A5062939922) · [6,586 citations](https://openalex.org/works?filter=author.id:A5062939922&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/kun-gai/#papers) · [🔗 Cited 73 times in our library](https://md.research.elamur.ai/free/en/authors/kun-gai/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #11346](https://md.research.elamur.ai/free/en/paper-stars/page/114/#star-11346) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Kun+Gai) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Kun+Gai) · [dblp](https://dblp.org/search?q=Kun+Gai) · [ACL Anthology](https://aclanthology.org/search/?q=Kun+Gai) ## Affiliations [🏢**Kuaishou** Beijing · China 2023–2026 · 82 papers*current*](https://md.research.elamur.ai/free/en/companies/kuaishou/) · [🎓**Klaipėda University** Klaipėda · Lithuania 2026 · 2 papers*current*](https://ror.org/027sdcz20) · [🎓**Peking University** Beijing · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/peking-university/) · [🏢**Shanghai Dramatic Arts Centre** Xuhui · China 2026 · 1 paper*current*](https://ror.org/057ydw805) · [🏥**Shanghai Xuhui Central Hospital** Shanghai · China 2026 · 1 paper*current*](https://ror.org/01whmzn59) · [🏢**Alibaba Group** Hangzhou · China 2012–2025 · 37 papers](https://md.research.elamur.ai/free/en/companies/alibaba-group/) · [🎓**Tsinghua University** Beijing · China 2008–2024 · 8 papers](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) · [🔬**State Key Laboratory of Intelligent Technology and Systems** Beijing · China 2009–2011 · 6 papers](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-intelligent-technology-and-systems/) · [🎓**Jinan University** Guangzhou · China 2018 · 2 papers](https://md.research.elamur.ai/free/en/universities/jinan-university/) 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. 📚 Shelves 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Decision Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · [Information Systems · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Management Science and Operations Research · 1 work](https://md.research.elamur.ai/free/en/shelves/decision-sciences/management-science-and-operations-research/) · [Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) ## Works by year ### 2020s [**2026** 4 papers](https://md.research.elamur.ai/free/en/authors/kun-gai/year/2026/) ## Papers The most cited first (OpenAlex and our library). 1. **[CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/su-2026-ce-gppo-coordinating-entropy-gradient/)** *(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](https://md.research.elamur.ai/free/en/papers/su-2026-entropy-ratio-clipping-as-soft/)** *(2026 · 1 citation)* LLM post-training with reinforcement learning is usually off-policy, so updates use samples from older policies. 3. **[DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing](https://md.research.elamur.ai/free/en/papers/zhang-2026-deepsynth-eval-objectively-evaluating-information/)** *(2026)* Deep Research agents are usually benchmarked on how well they find information. The stage after retrieval gets far less objective testing: merging evidence from many sources into a long, organized report. DeepSynth-Eval (DSE) targets that stage. The authors treat expert-written survey papers as reference answers. For… 4. **[Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers](https://md.research.elamur.ai/free/en/papers/zhang-2026-unleashing-native-recommendation-potential-llm/)** *(2026)* LLM-based generative recommenders must name items in a form the model can produce and that maps back to real catalog entries. ## All works 6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them. 1. **[Deep Interest Evolution Network for Click-Through Rate Prediction ↗](https://doi.org/10.1609/aaai.v33i01.33015941) Proceedings of the AAAI Conference on Artificial Intelligence · no summary yet**Guorui Zhou et al.*2019 · 1,102 citations* 2. **[Leanabell-Prover: Posttraining Scaling in Formal Reasoning ↗](https://arxiv.org/abs/2504.06122) arXiv:2504.06122 · no summary yet**Jingyuan Zhang et al.*2025 · 21 citations* 3. **[CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/su-2026-ce-gppo-coordinating-entropy-gradient/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zhenpeng Su, Leiyu Pan, Minxuan Lv, et al.*2026 · 7 citations* 4. **[Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/su-2026-entropy-ratio-clipping-as-soft/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Zhenpeng Su, Leiyu Pan, Minxuan Lv, et al.*2026 · 1 citation* 5. **[DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing](https://md.research.elamur.ai/free/en/papers/zhang-2026-deepsynth-eval-objectively-evaluating-information/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, et al.*2026* 6. **[Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers](https://md.research.elamur.ai/free/en/papers/zhang-2026-unleashing-native-recommendation-potential-llm/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Zhiyang Zhang, Junda She, Kuo Cai, et al.*2026* ## Co-authors here 12 of 15 co-authors with a page, the most papers together first. - [Guorui Zhou](https://md.research.elamur.ai/free/en/authors/guorui-zhou/) ×4 - [Ruiming Tang](https://md.research.elamur.ai/free/en/authors/ruiming-tang/) ×3 - [Han Li](https://md.research.elamur.ai/free/en/authors/han-li/) ×2 - [Leiyu Pan](https://md.research.elamur.ai/free/en/authors/leiyu-pan/) ×2 - [Minxuan Lv](https://md.research.elamur.ai/free/en/authors/minxuan-lv/) ×2 - [Wenping Hu](https://md.research.elamur.ai/free/en/authors/wenping-hu/) ×2 - [Yuntao Li](https://md.research.elamur.ai/free/en/authors/yuntao-li/) ×2 - [Zhenpeng Su](https://md.research.elamur.ai/free/en/authors/zhenpeng-su/) ×2 - [Bo Chen](https://md.research.elamur.ai/free/en/authors/bo-chen/) - [Fuzheng Zhang](https://md.research.elamur.ai/free/en/authors/fuzheng-zhang/) - [Shiyao Wang](https://md.research.elamur.ai/free/en/authors/shiyao-wang/) - [Tao Wang](https://md.research.elamur.ai/free/en/authors/tao-wang/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/) ×3: [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) ×3 - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×2: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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); [13 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/kun-gai/cited-by/). Updated 2 November 2026