Elamur Research⌕
☰
home / authors / Zefan Wang

Zefan Wang

Zefan Wang has 2 papers in our library, in 2025; often with Tianyu Yu, Weize Chen, Bingxiang He.

2 papers in our library · 2025

OpenAlex · ORCID · h-index 11 · 32 works · 646 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 173 times in our library · ⭐ Paper Stars ranking: #5920

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

🎓Tsinghua UniversityBeijing · China2021–2026 · 6 paperscurrent🎓Jinan UniversityGuangzhou · China2022–2024 · 6 papers🔬Institute of High Energy PhysicsBeijing · China2015–2022 · 5 papers🎓University of Science and Technology of ChinaHefei · China2015–2021 · 4 papers🎓University of Chinese Academy of SciencesBeijing · China2018–2022 · 3 papers🎓Nanyang Technological UniversitySingapore · Singapore2023–2024 · 2 papers🏛️Chinese Academy of SciencesBeijing · China2018–2022 · 2 papers🎓Hong Kong Polytechnic UniversityHong Kong · China2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 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

 Works by year

2020s

20252 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Process Reinforcement through Implicit Rewards (2025 · 151 citations)
    Reinforcement learning for LLM reasoning usually relies on one verifiable reward at the end of each response.
  2. MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe (2025 · 24 citations)
    MiniCPM-V 4.5 is an 8B-parameter multimodal LLM from OpenBMB. It targets three costly parts of MLLM development: long visual token sequences, brittle document-parsing pipelines and verbose reasoning. To shorten visual input, the authors extend the 2D-Resampler of earlier MiniCPM-V models into a unified 3D-Resampler.…

 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 173 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/zefan-wang/