Elamur Research⌕
☰
home / authors / Taiqiang Wu

Taiqiang Wu

Taiqiang Wu has 3 papers in our library, in 2025–2026, most of them on Language models & pretraining, Reasoning, Efficient models & compression; often with Runming Yang, Jiahao Wang, Ngai Wong.

3 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 5 · 54 works · 130 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 54 times in our library · ⭐ Paper Stars ranking: #7614

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

🎓University of Hong KongPok Fu Lam · China2023–2026 · 35 paperscurrent🎓Tsinghua UniversityBeijing · China2021–2026 · 8 paperscurrent🏢TencentShenzhen · China2022–2026 · 5 paperscurrent🏢JingdongBeijing · China2026 · 1 papercurrent🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China2021–2023 · 5 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 2 works

🧭 Topics 3Research subjects and languages the work is about.Efficient models & compression · 1 workLanguage models & pretraining · 1 workReasoning · 1 work

 Works by year

2020s

20262 papers20251 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025 · 47 citations)
    Distilling large language models usually means training a student to match the teacher's next-token distribution with a Kullback-Leibler loss.
  2. Revisiting Model Interpolation for Efficient Reasoning (2026 · 6 citations)
    The paper looks at efficient reasoning: how to keep the accuracy of long chain-of-thought models while producing fewer tokens.
  3. ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection (2026 · 4 citations)
    Standard supervised fine-tuning (SFT) trains an LLM to reproduce one reference answer token by token. Valid alternative phrasings are therefore penalized, and the model tends to memorize surface wording. Training on several references per prompt could help, but the authors find it expensive and unstable. They instead…

 Co-authors here

9 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 54 times (of the 149,439 papers whose bibliographies we read); 14 citing papers with a page here →.

Updated

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