Qingpeng Cai (蔡庆芃)

 




Qingpeng Cai is currently a Senior Staff Research Scientist at Kuaishou Technology, where he is responsible for business optimization and technical management. He received his Ph.D. from Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University. He received his B.E. from Nanjing University. His core research focuses on Reinforcement Learning and its applications to Large Language Models and practical domains (Recommender Systems and Advertising). He serves as Area Chair for top-tier machine learning conferences including NeurIPS, ICLR. He was awarded the 2024 Qian Weichang Prize for Chinese Information Processing Science and Technology (First Prize in Natural Sciences). Additionally, he led his team to win dual-track championships in the NeurIPS 2024 Auto-Bidding in Large-Scale Auctions Competition. In 2025, he proposed the Generative Model for RL (G4RL) bidding paradigm, which was fully applied to the advertising system, increasing the platform's revenue by more than 3%. More information can be found in Google Scholar, DBLP, Reinforcement Learning works in Kuaishou Technology

蔡庆芃目前在快手科技担任算法总监，负责业务优化和技术管理工作。他于清华大学交叉信息研究院获得博士学位，本科毕业于南京大学。他的研究兴趣专注在强化学习以及其在大语言模型以及实际问题（推荐、广告领域）的应用。他担任NeurIPS, ICLR等机器学习顶级会议的领域主席。他曾获得[2024年钱伟长中文信息处理科学技术奖（自然科学一等奖）]，并在NeurIPS 2024自动出价比赛中获得[双赛道冠军]。 他于2025年提出[生成式强化学习（Generative Model for RL，G4RL）出价范式]，全面应用在广告系统，平台收入提升超过3%。

Selected Invited Talks

Professional Activities

Preprint(* indicates the corresponding author)

Publications(* indicates the corresponding author)