Tianyu Yu

Tianyu Yu

Ph.D. Student

Tsinghua University

Biography

I am a Ph.D. student in Computer Technology at Tsinghua University, advised by Prof. Zhiyuan Liu. I received my bachelor’s degree in Software Engineering from Beihang University, advised by Prof. Si Liu and Prof. Ning Ge, and my master’s degree in Computer Technology from Tsinghua University, advised by Prof. Haitao Zheng. My current research focuses on efficient multimodal large language models and LLM/MLLM post-training. As a core contributor to the MiniCPM-V/o series, I mainly lead post-training for the model family.

Selected Publications

Deep Pre-Alignment for VLMs
Modular visual-encoder replacement for deeper multimodal pre-alignment.
Tianyu Yu, Kechen Fang, Zihao Wan, Kaidong Zhang, Yicheng Zhang, Jun Song, Bo Zheng, Yuan Yao ICML 2026
Paper Code
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
Real-time full-duplex omni-modal interaction via a unified streaming framework.
Junbo Cui, Bokai Xu, Chongyi Wang, Tianyu Yu, Weiyue Sun, Yingjing Xu, +28 more authors, Zhiyuan Liu, Yuan Yao Preprint
Paper Code
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
Efficient MLLM recipe across architecture, data, and training.
Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, +26 more authors, Zhiyuan Liu, Maosong Sun CVPR 2026
Paper Code
Efficient GPT-4V Level Multimodal Large Language Model for Deployment on Edge Devices
Efficient GPT-4V-level MLLMs for edge-device deployment.
Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, +16 more authors, Zhiyuan Liu, Maosong Sun Nature Communications 2025
Paper Code
RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
Open-source AI feedback for trustworthy MLLM alignment.
Tianyu Yu, Haoye Zhang, Qiming Li, Qixin Xu, Yuan Yao, Da Chen, +8 more authors, Tat-Seng Chua, Maosong Sun CVPR 2025 Highlight
Paper Code
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
Fine-grained correctional human feedback for reducing MLLM hallucination.
Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, +3 more authors, Maosong Sun, Tat-Seng Chua CVPR 2024
Paper Code
Cross-Modal Omni Interaction Modeling for Phrase Grounding
Cross-modal interaction modeling for phrase grounding.
Tianyu Yu, Tianrui Hui, Zhihao Yu, Yue Liao, Sansi Yu, Faxi Zhang, Si Liu ACM MM 2020
Paper

Honors & Awards

2024 Intel China Academic Achievement Award
2021 Outstanding Graduate of Beijing
2020 Beihang University Shenyuan Medal Nomination Award (the highest undergraduate honor, 10/3800+)
2019 National Scholarship for Undergraduates (top 1%)
2018 National Scholarship for Undergraduates (top 1%)

Contact

yiranytianyu@gmail.com Twitter / X