Name: Qingmao Yao I am a first-year Ph.D. student at Center on Frontiers of Computing Studies (CFCS), School of Computer Science, Peking University, advised by Prof. Xiaotie Deng. I received my bachelor’s degree from the School of Mathematical Sciences at Beihang University, advised by Prof. Xiao Zhang. My research focuses on advancing Decision Intelligence within complex, data-driven sequential decision-making environments. Specifically, I am interested in empowering agents with out-of-distribution generalization and robust exploration capabilities that surpass the limitations of offline datasets. Strategically, I leverage Large Language Models (LLMs), Offline Reinforcement Learning, and Generative Models to solve challenging, real-world problems, with a particular focus on auto-bidding in non-stationary auctions.

Email: qmyao25@stu.pku.edu.cn, qingmaoyao@163.com Google scholar: https://scholar.google.com/citations?user=KKVy_DEAAAAJ&hl=zh-CN&oi=ao

Publications Offline RL with smooth OOD generalization in convex hull and its neighborhood Qingmao Yao, Zhichao Lei, Tianyuan Chen, Ziyue Yuan, Xuefan Chen, Jianxiang Liu, Faguo Wu, Xiao Zhang ICLR 2025 https://arxiv.org/abs/2506.08417

Iterative Scarcity-Guided Exploration: Bootstrapping Generative Auto-bidding from Narrow Support Qingmao Yao, Guangzheng Hu, Yusen Huo, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, Xiaotie Deng ICLR 2026 Workshop AIMS https://openreview.net/forum?id=aTcHmMtkPR