Yaodong Yang 杨耀东 · Boya Young Scholar

Dr. Yaodong Yang is an Assistant Professor (Boya Young Scholar) and Assistant Dean at the Institute for Artificial Intelligence, Peking University, and Co-founder & Chief Scientist of PsiBot. His research centres on AI alignment — making intelligent systems reliably do what humans intend — with three focus areas: alignment among agents, using game theory and multi-agent reinforcement learning to bring large populations of learning agents to stable, cooperative collective behaviour; alignment between humans and models, using constrained preference learning and post-training to make large models both helpful and safe; and alignment with the physical world, enabling embodied agents to perceive, act and keep learning safely in real environments. All three share one methodological core: constrained reinforcement learning and multi-agent game-theoretic modelling.

He has published over 300 papers in venues including Nature Machine Intelligence, Matter, AIJ, JMLR and TPAMI, with more than 19,000 Google Scholar citations (h-index 60); he has been the top-ranked AI & ML scholar at Peking University on CSRankings since 2022 and is a Scopus World Top 2% Scientist. Recognition includes five best-paper-level awards (ACL 2025 Best Paper, UKRI AI Best Paper 2026, ICCV 2023 Best Paper Finalist, CoRL 2020 Best System Paper, AAMAS 2021 Blue Sky Idea Award), China's national young-talent programs, MIT Technology Review "AI 100 Young Innovators", Forbes China 2025 Innovative Leaders and the Wu Wenjun AI Science & Technology Award.

Beyond papers, his open-source toolkits — Safe-RLHF, OmniSafe, MARLlib, Bi-DexHands — are used by research groups worldwide, and through university–industry joint laboratories he has incubated two unicorn companies (valued at US$1B+), PsiBot (embodied foundation models) and Neo Matrix (world models). He teaches PKU's Foundations and Alignment of Large Language Models and Multi-Agent Systems, recognised by the PKU Teaching Achievement Award and the National Computer Teaching Case Competition; his students have won PKU's May-4th Medal, President's Scholarship and Annual Figures honours, as well as Tencent Hunyuan and SenseTime fellowships.

He serves as (Senior) Area Chair for ICML, ICLR, NeurIPS, AAAI, IJCAI, AAMAS and IROS, and as Associate Editor of TMLR, Neural Networks and Scientific Reports. Before joining PKU he was an Assistant Professor at King's College London, a Principal Researcher at Huawei R&D UK and a Senior Manager at AIG. He holds a B.Sc. from the University of Science and Technology of China, an M.Sc. from Imperial College London and a Ph.D. from University College London, where he was the university's sole nominee for the ACM SIGAI Doctoral Dissertation Award.