Elamur Research⌕
☰
home / authors / Zhezheng Hao

Zhezheng Hao

Zhezheng Hao has 3 papers in our library, in 2026, most of them on Language models & pretraining, Reasoning, Code & programming languages; often with Hande Dong, Hong Wang, Qiang Lin.

3 papers in our library · 2026

OpenAlex · ORCID · h-index 6 · 26 works · 135 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 30 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #8428

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Zhejiang UniversityHangzhou · China2026 · 14 paperscurrent🎓Fudan UniversityShanghai · China2026 · 1 papercurrent🎓Northwestern Polytechnical UniversityXi'an · China2023–2025 · 10 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

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

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArts and Humanities · 2 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 2 worksInformation Systems · 2 worksComputer Science Applications · 1 work

🧭 Topics 3Research subjects and languages the work is about.Reasoning · 1 workCode & programming languages · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20263 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective (2026 · 22 citations)
    Policy optimization in RLVR often suffers from entropy collapse. Policy entropy falls quickly, rollouts become uniform, and group-relative advantages (as in GRPO) stop separating good responses from bad ones. Existing fixes such as Clip-Higher, Positive-Reweighting and Entropy-Aware Advantage are largely heuristic…
  2. ReCreate: Reasoning and Creating Domain Agents Driven by Experience (2026 · 8 citations)
    Most practical LLM agents still depend on scaffolds that people write by hand: prompts, workflows, tools, and memory.
  3. GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026 · 1 citation)
    Group-relative RL methods such as GRPO and DAPO are popular for post-training code LLMs because they need no critic.

All works

5 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Rethinking Entropy Interventions in RLVR: An Entropy Change PerspectiveAnnual Meeting of the Association for Computational Linguistics (ACL)Zhezheng Hao, Hong Wang, Haoyang Liu, et al.2026 · 22 citations
  2. ReCreate: Reasoning and Creating Domain Agents Driven by ExperienceAnnual Meeting of the Association for Computational Linguistics (ACL)Zhezheng Hao, Hong Wang, Jian Luo, et al.2026 · 8 citations
  3. GAPO: Robust Advantage Estimation for Real-World Code LLMsFindings of the Association for Computational LinguisticsJianqing Zhang, Zhezheng Hao, Wei Xia, et al.2026 · 1 citation
  4. Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetJianqing Zhang et al.2026
  5. LEPO: Latent Reasoning Policy Optimization for Large Language Models ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetYuyan Zhou et al.2026

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 30 times (of the 149,439 papers whose bibliographies we read); 14 citing papers with a page here →.

Updated

↑ back to top

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