Scholar
Yaodong Yang
Google Scholar ID: 6yL0xw8AAAAJ
Boya (博雅) Assistant Professor at Peking University
Citations & Impact
Citations
10,789
H-index
48
i10-index
116
Publications
20
Co-authors
17
list available
Publications
Resume (English only)
Academic Achievements
- Published 200+ papers in top venues including Nature Machine Intelligence, Cell Matter, Artificial Intelligence Journal, and IEEE TPAMI
- Over 12,000 Google Scholar citations
- Ranked #1 at Peking University in AI & ML according to CSRankings since 2022
- Listed in Scopus Top 2% Scientists Worldwide
- ACL 2025 Best Paper Award
- ICCV 2023 Best Paper Initial List
- CoRL 2020 Best System Paper Award
- AAMAS 2021 Blue Sky Idea Award
- Named to MIT Technology Review’s “AI 100 Young Innovators”
- WAIC 2022 “Yunfan Star Award”
- ACM SIGAI China Rising Star Award
- Serves as Area Chair for ICML, ICLR, NeurIPS, AAAI, IJCAI, AAMAS, IROS
- Associate Editor for Scientific Reports, Transactions on Machine Learning Research, Neural Networks
- Champion of NeurIPS 2022 Dexterity Challenge (1st out of 340 teams)
- Led open-source RL projects: OmniSafe, HARL, MARLlib, MAlib, TorchOpt
Research Experience
- Currently leading the PKU Alignment & Interaction Lab (PAIR-Lab) at Peking University
- Former Assistant Professor at King’s College London
- Former Principal Researcher at Huawei Research U.K.
- Former Senior Manager at AIG
- Principal investigator of over 50 research projects funded by NSFC, Ministry of Science and Technology, Beijing Municipal Science & Technology Commission, and industry-university joint labs
Background
- Assistant Professor (Boya Young Scholar) at the Institute for Artificial Intelligence, Peking University
- Director of the AI Safety Centre at BAAI
- Chief Scientist of the PKU–PsiBot Joint Laboratory
- Recipient of China’s National High-level Overseas Talent Program, NSFC Excellent Young Scientists Fund (Overseas), and CAST Young Elite Scientists Sponsorship Program
- Research focuses on experience learning and alignment of AI agents, aiming to advance trustworthy deployment and real-world alignment of large models
- Research areas include reinforcement learning, AI alignment, and embodied intelligence
