Elamur Research⌕
☰
home / authors / Zeyu Li

Zeyu Li

Zeyu Li has 2 papers in our library, in 2018–2026, most of them on Language models & pretraining, Reasoning; often with Jieyu Zhao, Kai-Wei Chang, Shengjie Ma.

2 papers in our library · 2018–2026

OpenAlex · ORCID · h-index 21 · 96 works · 1,799 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 185 times in our library · ⭐ Paper Stars ranking: #3727

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

🏢General AtomicsSan Diego · United States2019–2026 · 23 paperscurrent🔬China Railway First Survey and Design Institute Group Co. Ltd.Xi'an2026 · 1 papercurrent🎓Georgia Institute of TechnologyAtlanta · United States2026 · 1 papercurrent🎓Peking UniversityBeijing · China2001–2025 · 31 papers🔬State Key Laboratory of Nuclear Physics and TechnologyBeijing2010–2025 · 14 papers🎓Oak Ridge Associated UniversitiesOak Ridge · United States2020–2024 · 7 papers🔬China Institute of Atomic EnergyBeijing · China2023–2025 · 4 papers🎓China Medical UniversityShenyang · China2023–2024 · 3 papers🏥Sheng Jing HospitalShenyang · China2023–2024 · 3 papers🎓University of Chinese Academy of SciencesBeijing · China2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 23 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 8The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksSocial Sciences · 1 workArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksGender Studies · 1 workSafety Research · 1 workComputer Vision and Pattern Recognition · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workReasoning · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.GloVe · 1 work

 Works by year

2020s

20261 paper

2010s

20181 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Learning Gender-Neutral Word Embeddings (2018 · 520 citations)
    Word vectors learned from human-written text tend to absorb social stereotypes. For example, gender-neutral occupations such as "programmer" or "nurse" end up leaning toward one gender, and this skew carries into downstream systems such as coreference. Earlier debiasing (Hard-GloVe, after Bolukbasi et al.) was a…
  2. Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026 · 10 citations)
    Process Reward Models (PRMs) score each step of an LLM's mathematical reasoning. They have two weaknesses: they can be gamed through reward hacking, and they need costly step-level annotation. They also penalize a wrong step even when a later step fixes it.

 Co-authors here

6 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 185 times (of the 149,439 papers whose bibliographies we read); 41 citing papers with a page here →.

Updated

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