Elamur Research⌕
☰
home / authors / ChunMing Wang

ChunMing Wang

ChunMing Wang has 3 papers in our library, in 2026, most of them on Language models & pretraining, Dialogue systems, Knowledge graphs & ontologies; often with Tong Ruan, Weiyan Zhang, Guangya Yu.

3 papers in our library · 2026

OpenAlex · h-index 0 · 7 works · 0 citations OpenAlex, 2026-10-14

📄 3 works in our library · ⭐ Paper Stars ranking: #13303

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

🔬Renji HospitalShanghai · China2026 · 3 paperscurrent🎓Shanghai Jiao Tong UniversityShanghai · China2026 · 3 paperscurrent

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 9The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksComputer Science · 3 worksHealth Informatics · 3 worksMedicine · 3 worksComputer Vision and Pattern Recognition · 2 worksArts and Humanities · 1 workHealth Information Management · 1 workHealth Professions · 1 workLanguage and Linguistics · 1 work

🧭 Topics 4Research subjects and languages the work is about.Dialogue systems · 1 workKnowledge graphs & ontologies · 1 workLanguage models & pretraining · 1 workVision & language · 1 work

 Works by year

2020s

20263 papers

 Papers

The most cited first (OpenAlex and our library).

  1. AIDA-SEAT: Towards Reliable AI Doctor Assistant via State-Evaluation-Action Tree Enhanced LLMs in Online Hospital (2026)
    Clinical assistants built on LLMs, whether prompted directly or grounded through text or graph retrieval (RAG), mostly receive isolated medical facts.
  2. Experience is the Teacher: Reusing Atomic Thoughts from LLMs to Improve Medical Dialogue (2026)
    LLMs used as doctor simulators tend to reason in one of two weak ways. Fixed, expert-written reasoning templates are rigid. Long test-time-scaling chains, as in R1-style models, are wasteful. This paper adapts the idea of reusable "atomic thoughts" (small, composable reasoning units) to medical dialogue.
  3. MedKInstruct: A Multimodal Knowledge Graph Based Framework for Multi-Hop and Hard-Negative Instruction Data Synthesis in MedVQA (2026)
    Medical visual question answering (MedVQA) models are often built by instruction-tuning general LVLMs on QA pairs that a strong model such as GPT-4o generates from image captions.

 Co-authors here

7 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/chunming-wang/