Research and Publications

My research is in theoretical computer science and learning theory, with current work on bandit learning, hybrid feedback, robustness, and influence maximization.

* Equal contribution.

Conference Proceedings

One Rounding Fits All: Memory-Efficient Approximation Algorithms for Partition-Constrained Influence Maximization

Qixin Zhang^* , Qirun Zeng^* , Hui Lu , Pingchuan Ma , Jinhang Zuo , Renqiang Luo , Yi Yu , Dacheng Tao

Studies memory-efficient approximation algorithms for influence maximization under partition constraints.

KDD'2026 Code

Fusing Reward and Dueling Feedback in Stochastic Bandits

Xuchuang Wang , Qirun Zeng , Jinhang Zuo , Xutong Liu , Mohammad Hajiesmaili , John C. S. Lui , Adam Wierman

Examines stochastic bandits with both reward observations and dueling feedback.

ICML'2025 Code

Preprints

Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback

Qirun Zeng , Xuchuang Wang , Jiayi Shen , Xutong Liu , Fang Kong , Jinhang Zuo

Studies best-arm identification in generalized linear bandits with hybrid feedback.

arXiv Code

Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injection

Qirun Zeng , Eric He , Richard Hoffmann , Xuchuang Wang , Jinhang Zuo

Studies adversarial attacks on stochastic bandit algorithms through fake data injection.

arXiv Code