Elamur Research⌕
☰
home / authors / Weijia Li

Weijia Li

Weijia Li has 2 papers in our library, in 2025–2026, most of them on Language models & pretraining, Vision & language, Efficient models & compression; often with Conghui He, Linfeng Zhang, Qintong Zhang.

2 papers in our library · 2025–2026

OpenAlex · ORCID · h-index 5 · 15 works · 71 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 22 times in our library · ⭐ Paper Stars ranking: #7959

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

🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2026 · 1 papercurrent🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China2026 · 1 papercurrent🎓Tsinghua UniversityBeijing · China2026 · 1 papercurrent🎓Sun Yat-sen UniversityGuangzhou · China2025 · 5 papers🎓Jimei UniversityXiamen · China2019–2024 · 5 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

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

 Works by year

2020s

20261 paper20251 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters More (2025 · 44 citations)
    Vision tokens make up most of the input to multimodal LLMs, which makes inference expensive. Most training-free pruning methods score each token's "importance" from attention maps and drop the low scorers. The authors argue this approach has four weaknesses. It treats scores as fixed even after other tokens are…
  2. RoZO: Geometry-Aware Zeroth-Order Fine-Tuning on Low-Rank Adapters for Black-Box Large Language Models (2026 · 1 citation)
    Fine-tuning large language models with back-propagation needs a lot of memory, because activations must be stored.

 Co-authors here

5 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 22 times (of the 149,439 papers whose bibliographies we read); 4 citing papers with a page here →.

Updated

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