Yixiu Mao

PhD student, Tsinghua University

Joined

September 2022

Names

Yixiu Mao (Preferred)

Emails

****@gmail.com (Confirmed)

****@mails.tsinghua.edu.cn (Confirmed)

****@alumni.sjtu.edu.cn (Confirmed)

Personal Links

Career & Education History

PhD student

Tsinghua University (mails.tsinghua.edu.cn)

2021 – Present

Undergrad student

Shanghai Jiao Tong University (sjtu.edu.cn)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Xiangyang Ji

2021 – Present

Expertise

No areas of expertise listed

Publications

A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization
Yiqin Lv, Zhiyu Mou, Miao Xu, Jinghao Chen, Cheems Wang, Yixiu Mao, Yun Qu, Rongquan Bai, Chuan Yu, Jian Xu, Bo Zheng, Xiangyang Ji
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
Zhiyu Mou, Yiqin Lv, Miao Xu, Cheems Wang, Yixiu Mao, Jinghao Chen, Qichen Ye, Chao Li, Rongquan Bai, Chuan Yu, Jian Xu, Bo Zheng
- ICLR 2026 Oral
- Readers: Everyone
Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
Heming Zou, Yixiu Mao, Yun Qu, Cheems Wang, Xiangyang Ji
- Submitted to ICLR 2026
- Readers: Everyone
Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
Yixiu Mao, Yun Qu, Cheems Wang, Heming Zou, Xiangyang Ji
- ICLR 2026 Poster
- Readers: Everyone
Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
Yun Qu, Cheems Wang, Yixiu Mao, Vincent Tao Hu, Björn Ommer, Xiangyang Ji
- KDD 2026
- Readers: Everyone
Model Predictive Task Sampling for Efficient and Robust Adaptation
Cheems Wang, Zehao Xiao, Yixiu Mao, Yun Qu, Jiayi Shen, Yiqin Lv, Xiangyang Ji
- Nature Communications (Accept in Principle)
- Readers: Everyone
Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
Yixiu Mao, Yun Qu, Cheems Wang, Xiangyang Ji
- NeurIPS 2025 spotlight
- Readers: Everyone
Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
Cheems Wang, Yiqin Lv, Yixiu Mao, Yun Qu, Yi Xu, Xiangyang Ji
- Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1 (KDD ’25), August 3–7, 2025, Toronto, ON, Canada.
- Readers: Everyone
Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
Yun Qu, Cheems Wang, Yixiu Mao, Yiqin Lv, Xiangyang Ji
- ICML 2025 poster
- Readers: Everyone
Adaptive HL-Gaussian: A Value Function Learning Method with Dynamic Support Adjustment
Chen Chen, Daming Shi, Yixiu Mao, Xiangyang Ji
- Submitted to ICLR 2025
- Readers: Everyone

View all 24 publications

Co-Authors

View all 34 co-authors