Publications

Papers are grouped by project completion year, with publication years shown in each entry.

Some papers appear under more than one topic. Use the filters below, or visit Research for an overview.

* Equal contribution. ** Alphabetical order. See Google Scholar for citation information.

2026

  1. textGrain: Entropy-Calibrated Watermarking for Language Model Text
    [Blog][Tech Report]
    Xiang Li, Garrett G. Wen, Xiaohong Chen, Qi Long, Arzav Jain, Florent Joly, Mike Lam, Qingquan Song, and Weijie J. Su
    Technical report accompanying the OpenAI blog, 2026
  2. Optimal Watermark Localization in Mixed-Source Large Language Model Texts
    [arXiv][Code]
    Jose H. Blanchet**, T. Tony Cai**, Xiang Li**, Hao Liu**, Qi Long**, and Weijie J. Su**
    arXiv preprint arXiv:2608.14906, 2026
  3. Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Text
    [arXiv][HTML][Code]
    Luxu Liang, and Xiang Li
    In Advances in Neural Information Processing Systems, 2026
  4. Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
    [arXiv][HTML][Code][Poster]
    Weiqing He*, Xiang Li*, Li Shen, Weijie J. Su, and Qi Long
    In International Conference on Learning Representations, 2026
  5. Selective Disclosure Watermarking for Large Language Models
    [arXiv][HTML][Code]
    Xuyang Chen, Xiang Li, Yangxinyu Xie, and Qi Long
    In International Conference on Machine Learning, 2026
  6. Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification
    [HTML]
    Jiayi Xin, Evan Qiang, Zihan Zhu, Xiang Li, Weijie J. Su, and Qi Long
    In Advances in Neural Information Processing Systems, 2026
  7. UCS: Estimating Unseen Coverage for Improved In-Context Learning
    [arXiv][HTML][Code]
    Jiayi Xin, Xiang Li, Evan Qiang, Weiqing He, Tianqi Shang, Weijie J. Su, and Qi Long
    In Findings of the Association for Computational Linguistics, 2026
  8. Weak Convergence Rates for Partial-Sum Processes of Nonlinear Stochastic Approximation
    [arXiv]
    Xiang Li, Jiadong Liang, and Zhihua Zhang
    arXiv preprint arXiv:2609.40338, 2026
  9. A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning
    [arXiv]
    Zijie Cheng, Xiang Li, Yang Peng, and Zhihua Zhang
    arXiv preprint arXiv:2608.27313, 2026

2025

  1. Optimal Detection for Language Watermarks with Pseudorandom Collision
    [arXiv][Code][Slides]
    T. Tony Cai**, Xiang Li**, Qi Long**, Weijie J. Su**, and Garrett G. Wen**
    arXiv preprint arXiv:2510.22007, 2025
  2. Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?
    [arXiv][Code][Poster][Slides]
    Xiang Li, Jiayi Xin, Qi Long, and Weijie J. Su
    arXiv preprint arXiv:2506.02058, 2025
  3. Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
    [arXiv][Code][Slides]
    Xiang Li, Garrett G. Wen, Weiqing He, Jiayuan Wu, Qi Long, and Weijie J. Su
    Journal of the American Statistical Association, 2026, Minor revision
  4. On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
    [arXiv][HTML][Code][Poster]
    Weiqing He*, Xiang Li*, Tianqi Shang, Li Shen, Weijie J. Su, and Qi Long
    In Advances in Neural Information Processing Systems, 2025, 🌟 Spotlight
  5. Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
    [arXiv][HTML][Code]
    Xiang Li*, Buxin Su*, Chendi Wang*, Qi Long, and Weijie J. Su
    In Advances in Neural Information Processing Systems, 2025, 🌟 Spotlight
  6. Robust Spectral Watermark for Synthetic Tabular Data
    [arXiv][HTML][Code]
    Yizhou Zhao, Xiang Li, Peter Song, Qi Long, and Weijie J. Su
    Statistical Learning and Data Science, 2026
  7. Discussion of “Balanced and Robust Randomized Treatment Assignments: The Finite Selection Model for the Health Insurance Experiment and Beyond”
    [HTML]
    Xiang Li, Yangxinyu Xie, and Weng-Kee Wong
    Journal of the Royal Statistical Society: Series A (Statistics in Society), 2026, Discussion article

2024

  1. A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency, and Optimal Rules
    [arXiv][HTML][Code][Poster][Slides]
    Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, and Weijie J. Su
    The Annals of Statistics, 2025, 🏛️ Invited talk at AoS invited paper session, JSM 2025
  2. Robust Detection of Watermarks in Large Language Models under Human Edits
    [arXiv][HTML][Code][Poster][Slides]
    Xiang Li, Feng Ruan, Huiyuan Wang, Qi Long, and Weijie J. Su
    Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2025, 🏛️ Invited talk at the JRSSb Editors Invited Session, RSS 2026, 🏆 IMS New Researcher Travel Award
  3. Debiasing Watermarks for Large Language Models via Maximal Coupling
    [arXiv][HTML][Code]
    Yangxinyu Xie, Xiang Li, Tanwi Mallick, Weijie J. Su, and Ruixun Zhang
    Journal of the American Statistical Association, 2025
  4. Decoupled Functional Central Limit Theorems for Two-Time-Scale Stochastic Approximation
    [arXiv][HTML]
    Yuze Han, Xiang Li, Jiadong Liang, and Zhihua Zhang
    Mathematics of Operations Research, 2026
  5. Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation
    [arXiv][HTML]
    Yuze Han, Xiang Li, and Zhihua Zhang
    Journal of Machine Learning Research, 2026
  6. Uncertainty Quantification of Data Shapley via Statistical Inference
    [arXiv]
    Mengmeng Wu, Zhihong Liu, Xiang Li, Ruoxi Jia, and Xiangyu Chang
    arXiv preprint arXiv:2407.19373, 2024
  7. Corruption-Robust Variance-Aware Algorithms for Generalized Linear Bandits under Heavy-Tailed Rewards
    [HTML]
    Qingyuan Yu, Euijin Baek, Xiang Li, and Qiang Sun
    In Conference on Uncertainty in Artificial Intelligence, 2025

2023

  1. Variance-Aware Decision Making with Linear Function Approximation under Heavy-Tailed Rewards
    [arXiv][HTML]
    Xiang Li, and Qiang Sun
    Transactions on Machine Learning Research, 2024, 🏛️ Invited to present in ICLR 2025
  2. Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data
    [arXiv][Code]
    Xiang Li, Jiadong Liang, and Zhihua Zhang
    Technical report, arXiv preprint arXiv:2302.07690, 2023
  3. Convergence and Inference of Stream SGD, with Applications to Queueing Systems and Inventory Control
    [arXiv][HTML][Code]
    Xiang Li*, Jiadong Liang*, Xinyun Chen, and Zhihua Zhang
    Operation Research, 2026
  4. Asymptotic Behaviors and Phase Transitions in Projected Stochastic Approximation: A Jump Diffusion Approach
    [arXiv]
    Jiadong Liang, Yuze Han, Xiang Li, and Zhihua Zhang
    Technical report, arXiv preprint arXiv:2304.12953, 2023

2022

  1. A Random Projection Approach to Personalized Federated Learning: Enhancing Communication Efficiency, Robustness, and Fairness
    [HTML]
    Yuze Han**, Shiyun Lin**, Xiang Li**, and Zhihua Zhang**
    Journal of Machine Learning Research, 2024, Extended version of the conference paper: Personalized federated learning towards communication efficiency, robustness and fairness
  2. Asymptotic Behaviors of Projected Stochastic Approximation: A Jump Diffusion Perspective
    [HTML][Slides]
    Jiadong Liang, Yuze Han, Xiang Li, and Zhihua Zhang
    In Advances in Neural Information Processing Systems, 2022, 🌟 Spotlight
  3. Personalized Federated Learning towards Communication Efficiency, Robustness, and Fairness
    [HTML][Code][Poster][Slides]
    Shiyun Lin*, Yuze Han*, Xiang Li, and Zhihua Zhang
    In Advances in Neural Information Processing Systems, 2022
  4. Statistical Analysis of Karcher Means for Random Restricted PSD Matrices
    [arXiv]
    Hengchao Chen, Xiang Li, and Qiang Sun
    In International Conference on Artificial Intelligence and Statistics, 2023

2021

  1. Statistical Estimation and Online Inference via Local SGD
    [arXiv][HTML][Slides]
    Xiang Li, Jiadong Liang, Xiangyu Chang, and Zhihua Zhang
    In Conference on Learning Theory, 2022
  2. FedPower: Privacy‑Preserving Distributed Eigenspace Estimation
    [arXiv][HTML]
    Xiao Guo, Xiang Li, Xiangyu Chang, Shusen Wang, and Zhihua Zhang
    Machine Learning, 2024, Extended version of the conference paper: Communication-efficient distributed SVD via local power iterations
  3. A Statistical Analysis of Polyak-Ruppert Averaged Q-Learning
    [arXiv][Code][Poster][Slides][Video]
    Xiang Li, Wenhao Yang, Jiadong Liang, Zhihua Zhang, and Michael I Jordan
    In International Conference on Artificial Intelligence and Statistics, 2023

2020

  1. Communication-Efficient Distributed SVD via Local Power Iterations
    [arXiv][HTML][Code][Poster][Slides]
    Xiang Li, Shusen Wang, Kun Chen, and Zhihua Zhang
    In International Conference on Machine Learning, 2021
  2. Finding Near Optimal Policies via Reducive Regularization in Markov Decision Processes
    [arXiv][HTML]
    Wenhao Yang, Xiang Li, Guangzeng Xie, and Zhihua Zhang
    In Workshop on Reinforcement Learning Theory, ICML, 2021

2019

  1. On the Convergence of FedAvg on Non-IID Data
    [arXiv][HTML][Code][Poster][Slides]
    Xiang Li*, Kaixuan Huang*, Wenhao Yang*, Shusen Wang, and Zhihua Zhang
    In International Conference on Learning Representations, 2020, 🎤 Oral presentation
  2. A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning
    [arXiv][HTML]
    Wenhao Yang*, Xiang Li*, and Zhihua Zhang
    In Advances in Neural Information Processing Systems, 2019
  3. Do Subsampled Newton Methods Work for High-Dimensional Data?
    [arXiv][HTML]
    Xiang Li, Shusen Wang, and Zhihua Zhang
    In AAAI Conference on Artificial Intelligence, 2020
  4. Communication Efficient Decentralized Training with Multiple Local Updates
    [arXiv]
    Xiang Li, Wenhao Yang, Shusen Wang, and Zhihua Zhang
    Technical report, arXiv preprint arXiv:1910.09126, 2019