Elamur Research⌕
☰
home / authors / Zhihua Wei

Zhihua Wei

Zhihua Wei has 2 papers in our library, in 2022–2026, most of them on Language models & pretraining; often with Chengyi Wang, Long Zhou, Qiang Li.

2 papers in our library · 2022–2026

OpenAlex · ORCID · Wikidata · h-index 21 · 176 works · 1,912 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 76 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #6267

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

🎓Tongji UniversityShanghai · China2007–2026 · 134 paperscurrent🎓Zhengzhou UniversityZhengzhou · China2024–2026 · 3 paperscurrent🎓Wuhan University of TechnologyWuhan · China2009–2013 · 10 papers🎓Xiamen UniversityXiamen · China2025 · 4 papers🎓Nanjing UniversityNanjing · China2012–2013 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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 6The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArts and Humanities · 1 workArtificial Intelligence · 1 workLanguage and Linguistics · 1 workSignal Processing · 1 workComputer Vision and Pattern Recognition · 1 work

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

 Works by year

2020s

20261 paper20221 paper

 Papers

The most cited first (OpenAlex and our library).

  1. SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing (2022 · 219 citations)
    Most self-supervised speech models learn only from untranscribed audio and pre-train only an encoder. As a result, they ignore text data and leave decoders for generation tasks untrained. SpeechT5, inspired by T5, treats every spoken language task as turning speech or text into speech or text. A single Transformer…
  2. Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement (2026)
    LVLMs often misdescribe what objects in an image are doing, for example claiming a woman rides a bicycle when she is actually pushing it.

All works

3 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. SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language ProcessingAnnual Meeting of the Association for Computational Linguistics (ACL)Junyi Ao, Rui Wang, Long Zhou, et al.2022 · 219 citations
  2. Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networks ↗arXiv:2111.10545 · no summary yetHanning Gao et al.2021 · 1 citation
  3. Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual EnhancementAnnual Meeting of the Association for Computational Linguistics (ACL)Zhenxin Qin, Qiang Li, Qingzhuo Wang, et al.2026

 Co-authors here

11 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 76 times (of the 149,439 papers whose bibliographies we read); 23 citing papers with a page here →.

Updated

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