Elamur Research⌕
☰
home / authors / Zhenyang Cai

Zhenyang Cai

Zhenyang Cai has 3 papers in our library, in 2024–2026, most of them on Language models & pretraining, Reasoning, Semitic languages; often with Benyou Wang, Bang An, Haizhou Li.

3 papers in our library · 2024–2026

OpenAlex · ORCID · h-index 2 · 6 works · 9 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 92 times in our library · ⭐ Paper Stars ranking: #7904

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

🎓Chinese University of Hong Kong, ShenzhenShenzhen · China2025–2026 · 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 8The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArts and Humanities · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksMedicine · 2 worksComputer Vision and Pattern Recognition · 2 worksHealth Informatics · 2 worksRadiology, Nuclear Medicine and Imaging · 1 work

🧭 Topics 4Research subjects and languages the work is about.Reasoning · 1 workLanguage models & pretraining · 2 worksSemitic languages · 1 workVision & language · 1 work

 Works by year

2020s

20261 paper20242 papers

 Papers

The most cited first (OpenAlex and our library).

  1. HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs (2024 · 87 citations)
    Work that reproduces OpenAI o1-style reasoning has mostly targeted mathematics. Medicine also needs careful step-by-step reasoning, but a clinical chain of thought is hard to check automatically. The authors address this by building verifiable medical problems. They start from 192K multiple-choice exam questions…
  2. Alignment at Pre-training! Towards Native Alignment for Arabic LLMs (2024 · 14 citations)
    Most LLM alignment work happens after pre-training, through instruction tuning or reinforcement learning from feedback. The authors ask whether alignment can start earlier, inside the pre-training corpus itself. They call this "native alignment" and test it on Arabic. Their pipeline has four steps:
  3. Towards a Radiologist Imitation Framework for 3D CT Diagnosis with Multimodal LLMs (2026)
    Most AI systems for 3D CT give every slice equal weight. Yet diagnostically relevant findings are usually concentrated in a few slices, so this uniform treatment wastes compute and can miss subtle lesions. The authors propose a framework that mimics how radiologists read a scan, in three stages. First, a CLIP-based…

 Co-authors here

12 of 13 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 92 times (of the 149,439 papers whose bibliographies we read); 43 citing papers with a page here →.

Updated

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