Elamur Research⌕
☰
home / authors / Zeli Su

Zeli Su

Zeli Su has 2 papers in our library, in 2026, most of them on Language models & pretraining, Low-resource languages, Vision & language; often with Guixian Xu, Xuexian Song, Ziyin Zhang.

2 papers in our library · 2026

OpenAlex · h-index 1 · 16 works · 1 citations OpenAlex, 2026-10-14

📄 2 works in our library · ⭐ Paper Stars ranking: #14110

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

🎓Minzu University of ChinaBeijing · China2025–2026 · 10 paperscurrent🏢Ant GroupHangzhou · China2026 · 4 paperscurrent🎓Peking UniversityBeijing · China2026 · 2 paperscurrent🎓Ningxia Medical UniversityYinchuan · China2017–2020 · 2 papers🏥Ningxia Medical University General HospitalYinchuan · China2017–2020 · 2 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).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 1 workLow-resource languages · 1 workVision & language · 1 work

 Works by year

2020s

20262 papers

 Papers

The most cited first (OpenAlex and our library).

  1. FTibSuite: A Comprehensive Resource Suite for Tibetan Vision–Language Modeling (2026)
    Tibetan has been largely left out of recent progress in vision–language models. It lacks image–text data, multimodal instruction sets and standardized benchmarks, so Tibetan VLM results are hard to reproduce or compare. The authors address this with FTibSuite, which has three parts:
  2. Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax (2026)
    When LLMs are adapted to a poorly supported language, they often lose ground on skills they already had. This is known as the alignment tax. The authors blame supervised fine-tuning (SFT): its token-level likelihood objective forces the model to copy small, skewed datasets, which overwrites pretrained knowledge. They…

 Co-authors here

8 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.

Updated

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