Elamur Research⌕
☰
home / authors / Qingfu Zhu

Qingfu Zhu

Qingfu Zhu has 5 papers in our library, in 2025–2026, most of them on Language models & pretraining, Reasoning, Vision & language; often with Wanxiang Che, Xianzhen Luo, Dingzirui Wang.

5 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 10 · 64 works · 394 citations OpenAlex, 2026-10-14

📄 5 works in our library · 🔗 Cited 96 times in our library · ⭐ Paper Stars ranking: #8256

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

🎓Harbin Institute of TechnologyHarbin · China2018–2026 · 41 papersEducationEmploymentcurrent🔬China Institute of Atomic EnergyBeijing · China2005–2024 · 11 papers🏛️China National Nuclear CorporationBeijing · China2018–2021 · 5 papers🎓University of California, Santa BarbaraSanta Barbara · United States2020–2021 · 2 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).Arts and Humanities · 5 worksComputer Science · 5 worksArtificial Intelligence · 5 worksLanguage and Linguistics · 5 worksComputer Vision and Pattern Recognition · 4 worksInformation Systems · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 2 worksReasoning · 2 worksVision & language · 1 work

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

 Works by year

2020s

20263 papers20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling (2025 · 22 citations)
    LLM inference is slow because autoregressive decoding emits one token per step, and each step is dominated by memory transfer of billions of weights.
  2. RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals (2025 · 10 citations)
    Reasoning LLMs that produce Long CoT have become strong at table question answering. However, building them requires costly training on curated data, and their long outputs tend to lose track of the table and invent cell contents. The authors (Harbin Institute of Technology) propose Row-of-Thought (RoT), a method…
  3. Scaling Laws for Code: A More Data-Hungry Regime (2026 · 3 citations)
    Scaling laws, which predict validation loss from model size (N), training tokens (D) and compute (C), have mostly been derived on natural language (NL).
  4. Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards (2026)
    Most multimodal work on visualization-to-code targets static charts. Real data exploration, however, often happens in interactive dashboards. This paper introduces Dashboard2Code, a task in which a model must explore a live dashboard on its own by clicking, hovering, filtering or dragging. It collects screenshots…
  5. Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format (2026)
    Parallel test-time scaling (TTS) usually samples many answers using a single reasoning format chosen by a human.

 Co-authors here

12 of 17 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 96 times (of the 149,439 papers whose bibliographies we read); 36 citing papers with a page here →.

Updated

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