Elamur Research⌕
☰
home / authors / Haozhan Li

Haozhan Li

Haozhan Li has 2 papers in our library, in 2025, most of them on Language models & pretraining, Reasoning; often with Ganqu Cui, Yuchen Zhang, Yuxin Zuo.

2 papers in our library · 2025

OpenAlex · h-index 4 · 16 works · 99 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 170 times in our library · ⭐ Paper Stars ranking: #6723

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

🎓Tsinghua UniversityBeijing · China2025–2026 · 4 paperscurrent🎓Shenyang Jianzhu UniversityShenyang · China2026 · 1 papercurrent🎓Communication University of ChinaBeijing · China2021–2024 · 7 papers🔬State Key Laboratory of Media Convergence and CommunicationBeijing2021–2024 · 5 papers🎓Tianjin University of TechnologyTianjin · China2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

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

📚 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

20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. 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.
  2. TTRL: Test-Time Reinforcement Learning (2025 · 76 citations)
    Reinforcement learning is now a main way to strengthen reasoning in large language models, but it usually needs labeled answers.

 Co-authors here

12 of 18 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 170 times (of the 149,439 papers whose bibliographies we read); 62 citing papers with a page here →.

Updated

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