Yuan Yao

Yuan Yao is an AI researcher whose work spans natural language processing and multimodal models for edge devices. They earned bachelor's and doctoral degrees in computer science and technology at Tsinghua and coauthored a 2022 paper on prompt tuning for discriminative language models. They worked as a postdoctoral fellow at the National University of Singapore and lead the MiniCPM-V and MiniCPM-o series of efficient multimodal models. Since January 2026, they are an assistant professor at Tsinghua's College of AI, researching multimodal large models and natural language processing.

Now at: Tsinghua University

Timeline

2014–2018

A Tsinghua bachelor's degree

Yao studies in Tsinghua's Department of Computer Science and Technology from August 2014 to July 2018 and earns a bachelor's degree there in 2018.
2022

Prompt tuning for language models

The 2022 paper DPT names Yao as a coauthor and presents prompt tuning for discriminative pretrained language models, recasting NLP tasks as discriminative language modeling.
2023

A doctorate at Tsinghua

They complete a PhD in computer science and technology at Tsinghua in 2023 after studying from August 2018 to July 2023, advised by Zhiyuan Liu at the Tsinghua Natural Language Processing Lab.
September 2023

Postdoctoral fellow at NUS

In September 2023, they begin work at the School of Computing, National University of Singapore, as a postdoctoral research fellow in NExT++ Lab with Professor Tat-Seng Chua.
2024–2025

MiniCPM-V for edge devices

Yao leads the MiniCPM-V and MiniCPM-o series of efficient multimodal large language models. In August 2024, they coauthor the MiniCPM-V paper on edge-device deployment; Nature Communications publishes their study in July 2025.
Since January 2026

Assistant professor at Tsinghua

In January 2026, they join Tsinghua University's College of AI as an assistant professor, where their research focuses on multimodal large models and natural language processing.