representative publications

@inproceedings{wang2025fusing,
  title = {Fusing Reward and Dueling Feedback in Stochastic Bandits},
  author = {Wang, Xuchuang and Zeng, Qirun and Zuo, Jinhang and Liu, Xutong and Hajiesmaili, Mohammad and Lui, John C.S. and Wierman, Adam},
  booktitle = {Forty-second International Conference on Machine Learning},
  year = {2025},
  significance = {Develops bandit algorithms that simultaneously consume absolute reward feedback and pairwise dueling comparisons -- a step toward learners that handle the heterogeneous human feedback found in modern RLHF-style applications.}
}

@inproceedings{wang2025robust,
  title = {Stochastic Bandits Robust to Adversarial Attacks},
  author = {Wang, Xuchuang and Liu, Maoli and Zuo, Jinhang and Liu, Xutong and Lui, John C.S. and Hajiesmaili, Mohammad},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
  significance = {Provides regret guarantees for stochastic bandits against a strong adversary that can corrupt rewards after observing the learner's actions, making bandit learning usable in settings where some feedback is manipulated.}
}

@inproceedings{wang2025asynchronous,
  title = {Asynchronous Multi-Agent Bandits: Fully Distributed vs. Leader-Coordinated Algorithms},
  author = {Wang*, Xuchuang and Chen*, Yu-Zhen Janice and Yang, Lin and Liu, Xutong and Hajiesmaili, Mohammad and Towsley, Don and Lui, John C.S.},
  booktitle = {ACM International Conference on Measurement and Modeling of Computer Systems},
  year = {2025},
  significance = {Drops the lock-step assumption that pervades multi-agent bandit analyses and compares fully distributed against leader-coordinated protocols, clarifying the communication-versus-regret tradeoff that governs how cooperating learners should share information.}
}

@inproceedings{wang2025best,
  title = {Best Arm Identification with Quantum Oracles},
  author = {Wang, Xuchuang and Chen, Yu-Zhen Janice and Guedes de Andrade, Matheus and Allcock, Jonathan and Hajiesmaili, Mohammad and Lui, John C.S. and Towsley, Don},
  booktitle = {The 39th Annual AAAI Conference on Artificial Intelligence},
  year = {2025},
  significance = {Studies best-arm identification when the learner can issue quantum queries to the reward oracle, quantifying the speedup that quantum-enhanced sequential decision-making offers over classical bandit algorithms.}
}

@inproceedings{wang2025learn,
  title = {Learning Best Paths in Quantum Networks},
  author = {Wang, Xuchuang and Liu, Maoli and Liu, Xutong and Li, Zhuohua and Hajiesmaili, Mohammad and Lui, John C.S. and Towsley, Don},
  booktitle = {Proceedings of the IEEE Conference on Computer Communications},
  year = {2025},
  significance = {Casts entanglement path selection in quantum networks as an online learning problem and gives a routing algorithm that adapts to unknown, noisy link fidelities -- a building block for routing on the quantum internet.}
}