Elamur Research⌕
☰
home / authors / Tianhao Li

Tianhao Li

Tianhao Li has 4 papers in our library, in 2023–2026, most of them on Language models & pretraining, Multilingual & cross-lingual NLP; often with Baosong Yang, Haoran Wei, Huan Lin.

4 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 2 · 7 works · 31 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 91 times in our library · ⭐ Paper Stars ranking: #7801

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

🏢Alibaba GroupHangzhou · China2023–2026 · 4 paperscurrent🏢Alibaba GroupGeorge Town · Cayman Islands2025–2026 · 3 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution 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 · 4 worksComputer Science · 4 worksArtificial Intelligence · 4 worksLanguage and Linguistics · 4 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 4 worksMultilingual & cross-lingual NLP · 2 works

 Works by year

2020s

20263 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. PolyLM: An Open Source Polyglot Large Language Model (2023 · 103 citations)
    Most open LLMs are trained mainly on English, so they handle many widely spoken languages poorly. Open multilingual instruction data and a shared multilingual evaluation suite are also missing. Researchers at Alibaba's DAMO Academy tackle all three gaps. They pre-train PolyLM from scratch in two sizes, 1.7B and 13B…
  2. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models (2026 · 3 citations)
    Sparse autoencoders (SAEs) break LLM hidden states into a small number of interpretable directions. In practice, though, they have mostly been used to inspect and label features after the fact, not to build or fix models. The Qwen Team addresses this with Qwen-Scope, an openly released collection of SAEs trained on…
  3. A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAMΔ Integration into Upcycled MoE (2026)
    Adding a new language to an LLM normally requires continued pre-training (CPT) followed by costly alignment, including SFT and RL on large instruction sets.
  4. Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs (2026)
    Most work on adversarial prompting treats a prompt as one undivided string. This paper argues instead that prompts are built from functional parts, and that these parts differ in how easily an attack can exploit them.

 Co-authors here

12 of 19 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 91 times (of the 149,439 papers whose bibliographies we read); 27 citing papers with a page here →.

Updated

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