Scholar

Yuan Yao

Google Scholar ID: 3NWfi3YAAAAJ

Postdoc Research Fellow, National University of Singapore

Multimodal LLMsNatural Language Processing

Citations & Impact

All-time

Citations

7,058

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Published multiple papers as first or corresponding author in top venues including Nature Communications, CVPR, ACL, ECCV, and COLM.
Led MiniCPM-V: A GPT-4V level multimodal LLM running on mobile devices, published in Nature Communications (2025).
Led MiniCPM-o: A GPT-4o level MLLM supporting vision, speech, and multimodal live streaming on phones (2025).
Contributed to key works such as RLAIF-V (CVPR 2025), GUICourse (ACL 2025), and AdaNAT (ECCV 2024).
Core contributor to the MiniCPM series, advancing end-side large language models (COLM 2024).

Background

Currently a Postdoc Research Fellow at the NExT++ Lab, School of Computing, National University of Singapore, working with Professor Chua Tat-Seng.
Research interests include multimodal large language models (MLLMs) and natural language processing (NLP).
Leads the MiniCPM-V and MiniCPM-o series of efficient multimodal large language models.
Will join the College of AI, Tsinghua University as a Tenure-track Assistant Professor in October 2025.
Actively seeking highly motivated PhD students and research interns interested in multimodal large language models.

Co-authors

13 total