Yue Xing, Xiaofeng Lin, Chenheng Xu, Namjoon Suh, Qifan Song, Guang Cheng, Benefits of Transformer: In-Context Learning in Linear Regression Tasks with Unstructured Data. arXiv
Yue Xing with Tony Sit and Zexi Cai, Online Censored Quantile Regression.
Xunlei Qian, Yue Xing. Ensuring Calibration Robustness in Split Conformal Prediction Under Adversarial Attacks. arXiv
Weiyi He, Yue Xing. Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression. arXiv
Meiqi Liu, Zhuoqun Huang, Yue Xing. How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model? arXiv
Pengfei He*, Yue Xing*, Shen Dong, Juanhui Li, Zhenwei Dai, Xianfeng Tang, Hui Liu, Han Xu, Zhen Xiang, Charu C. Aggarwal, Hui Liu, Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS. arXiv
Pengfei He, Yue Xing, Han Xu, Zhen Xiang, Jiliang Tang, Multi-Faceted Studies on Data Poisoning can Advance LLM Development. arXiv
Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, Qi He, Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems. arXiv
Pengfei He, Zhenwei Dai, Bing He, Hui Liu, Xianfeng Tang, Hanqing Lu, Juanhui Li, Jiayuan Ding, Subhabrata Mukherjee, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin. TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use. arXiv
Jie Ren, Yue Xing, Yingqian Cui, Charu C Aggarwal, Hui Liu, SoK: Machine Unlearning for Large Language Models. arXiv
Jie Ren, Yingqian Cui, Chen Chen, Vikash Sehwag, Yue Xing, Jiliang Tang, Lingjuan Lyu, EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations. arXiv
Yingqian Cui, Zhenwei Dai, Pengfei He, Bing He, Hui Liu, Xianfeng Tang, Jingying Zeng, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin. Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search. arXiv
Shen Dong, Mingxuan Zhang, Pengfei He, Li Ma, Bhavani Thuraisingham, Hui Liu, Yue Xing. PEAR: Planner-Executor Agent Robustness Benchmark. arXiv
Rajdeep Haldar, Ziyi Wang, Guang Lin, Yue Xing, Qifan Song. LLM Safety Alignment is Divergence Estimation in Disguise. NeurIPS2025. arXiv
Yue Xing, Adversarial Training in High-Dimensional Regression: Generated Data and Neural Networks. AISTATS2025. SSRN
Yingqian Cui, Jie Ren, Pengfei He, Hui Liu, Jiliang Tang, Yue Xing, Superiority of Multi-Head Attention in In-Context Linear Regression. AISTATS2025. arXiv
Yingqian Cui, Pengfei He, Xianfeng Tang, Qi He, Chen Luo, Jiliang Tang, Yue Xing, A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration. AISTATS2025. arXiv
Rajdeep Haldar, Yue Xing, Qifan Song (2024), Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability. AISTATS2024. arXiv
Yue Xing, Xiaofeng Lin, Qifan Song, Yi Xu, Belinda Zeng, Guang Cheng (2024), Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective. AISTATS2024. arXiv
Yue Xing, Qifan Song, Guang Cheng. Why Do Artificially Generated Data Help Adversarial Robustness. Neurips 2022. Openreview
Yue Xing, Qifan Song, Guang Cheng, Phase Transition from Clean Training to Adversarial Training. Neurips 2022. Openreview
Yue Xing, Qifan Song, Guang Cheng, Unlabelled Data Helps: Statistical Minimax Analysis and Adversarial Robustness. AISTATS 2022. arXiv
Yue Xing, Qifan Song, Guang Cheng, On the Algorithmic Stability of Adversarial Training. Neurips 2021. Openreview
Yue Xing, Ruizhi Zhang, Guang Cheng, Adversarially Robust Estimate and Risk Analysis in Linear Regression. AISTATS 2021. axXiv
Yue Xing, Qifan Song, Guang Cheng, On the Generalization Properties of Adversarial Training. AISTATS 2021. arXiv
Yue Xing, Qifan Song, Guang Cheng, Predictive Power of Nearest Neighbors Algorithm under Random Perturbation. AISTATS 2021. arXiv
Shih-Kang Chao, Zhanyu Wang, Yue Xing, Guang Cheng, Directional Pruning of Deep Neural Networks. Neurips 2020. arXiv
Jie Ren, Zhenwei Dai, Xianfeng Tang, Yue Xing, Shenglai Zeng, Hui Liu, Jingying Zeng, Qiankun Peng, Samarth Varshney, Suhang Wang, Qi He, Charu C. Aggarwal, Hui Liu, Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy. NeurIPS2025. arXiv
Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang, Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data. EMNLP2025 Main. arXiv
Pengfei He, Zitao Li, Yue Xing, Yaling Li, Jiliang Tang, Bolin Ding, Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning. EMNLP2025 Findings. arXiv
Jie Ren, Zhenwei Dai, Xianfeng Tang, Hui Liu, Jingying Zeng, Zhen Li, Rahul Goutam, Suhang Wang, Yue Xing, Hui Liu, Qi He, A General Framework to Enhance Fine-tuning-based LLM Unlearning. ACL2025 Findings. arXiv
Shenglai Zeng, Pengfei He, Kai Guo, Tianqi Zheng, Hanqing Lu, Yue Xing, Hui Liu, Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach. ACL2025 Main. arXiv
Bo Wang, Weiyi He, Pengfei He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang, Unveiling Privacy Risks in LLM Agent Memory. ACL2025 Main. arXiv
Pengfei He, Yupin Lin, Shen Dong, Han Xu, Yue Xing, Hui Liu, Red-Teaming LLM Multi-Agent Systems via Communication Attacks. ACL2025 Findings. arXiv
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He, Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models. ACL2025 Findings. arXiv
Jie Ren, Kangrui Chen, Yingqian Cui, Shenglai Zeng, Hui Liu, Yue Xing, Jiliang Tang, Lingjuan Lyu, Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models. CVPR2025. arXiv
Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang, Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective. arXiv
Pengfei He, Han Xu, Yue Xing, Hui Liu, Makoto Yamada, Jiliang Tang, Data Poisoning for In-Context Learning. NAACL2025. arXiv
Jie Ren, Kangrui Chen, Chen Chen, Vikash Sehwag, Yue Xing, Jiliang Tang, Lingjuan Lyu (2025), Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Model. WWW2025. arXiv
Yuping Lin*, Pengfei He*, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, Jiliang Tang (2024), Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis. EMNLP2024. arXiv
Jie Ren*, Yaxin Li*, Shenglai Zen, Han Xu, Lingjuan Lyu, Yue Xing, Jiliang Tang (2024), Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention. ECCV2024. arXiv
Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Jiliang Tang, Dawei Yin (2024), Exploring Memorization in Fine-Tuned Language Models. ACL2024 main. arXiv
Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, Jiliang Tang (2024), The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG). ACL2024 findings. arXiv
Rajdeep Haldar, Yue Xing, Qifan Song, Guang Lin, Adversarial Vulnerability as a Consequence of On-Manifold Inseparibility. TMLR, 2025. arXiv
Yue Xing, Alireza Aghasi, Saeed Ghadimi, High-Dimensional Regression with Missing Data: An Asymptotic Study. Stat, 2025.
Pengfei He, Yingqian Cui, Han Xu, Hui Liu, Makoto Yamada, Jiliang Tang, Yue Xing (2025), Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study. Stat, AI special issue. M3L and SFLLM NeurIPS 2024. arXiv
Yingqian Cui, Jie Ren, Han Xu, Pengfei He, Hui Liu, Lichao Sun, Yue Xing, Jiliang Tang, DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models. ACM SIGKDD Explorations Newsletter 26.2 (2025): 60-75. arXiv
Yingqian Cui, Jie Ren, Yuping Lin, Han Xu, Pengfei He, Yue Xing, Wenqi Fan, Hui Liu, Jiliang Tang, FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models.ACM SIGKDD Explorations Newsletter 26.2 (2025): 76-88. arXiv
Pengfei He, Yue Xing, Han Xu, Jie Ren, Yingqian Cui, Shenglai Zeng, Jiliang Tang, Makoto Yamada, Mohammad Sabokrou (2024), Stealthy Backdoor Attack via Confidence-driven Sampling. TMLR. arXiv
Alireza Aghasi, Saeed Ghadimi, Yue Xing, Mohammad Javad Feizollahi (2024), An Adversarially Robust Formulation of Linear Regression with Missing Data. IEEE Transactions on Signal Processing. link
Yue Xing, Ashutosh Pandey, David Yan, Fei Wu, Pamela Bhattacharya (2023), Ranked Pruning of Data Set to Train Machine Learning Models, US Patent, US18169462.
Tony Sit, Yue Xing (2023), Distributed Censored Quantile Regression. Journal of Computational and Graphical Statistics. link
Yue Xing, Qifan Song, Guang Cheng (2022), Benefit of Interpolation in Nearest Neighbor Algorithms. SIAM Journal on Mathematics of Data Science, Vol. 4, Issue 2, 2022. Link to journal version, arXiv1, arXiv2, code.
Yue Xing, Tony Sit, Hoi Ying Wong (2021), Variance Reduction for Risk Measures with Importance Sampling in Nested Simulation. Quantitative Finance. link
Tony Sit, Yue Xing, Yongze Xu, Minggao Gu. Pseudo Value Method for Ultra High-Dimensional Semiparametric Models with Life-Time Data, Statistica Sinica, Vol 29 No. 4 (2019) .
Interdisciplinary Projects
AI system for Statistics education, now supports STT802, STT481, CMSE381.
Personalized learning and AI system for Next Generation Science Assessment. Project news
Subjective-Objective-Assessment-Plan notes using Large Language Models. Website
Namsoo Shin, Xunlei Qian, Hang Li, Yucheng Chu, Cory Miller, Joseph Krajcik, Jiliang Tang, Yue Xing. A Generative AI Framework for Analyzing Student Responses in Formative Assessments to Provide Targeted Feedback. Submitted.
Namsoo Shin, Xunlei Qian, Yucheng Chu, Hang Li, Cory Miller, Joseph Krajcik, Yue Xing. AI in assessment. Paper presented at the Global Initiative in AI and Emerging Technologies in STEM Education. 2025.
Namsoo Shin, Xunlei Qian, Yucheng Chu, Hang Li, Cory Miller, Joseph Krajcik, Yue Xing. Multi-agent systems for detecting uncertainty and weaknesses in elementary students' written responses to usable knowledge tasks. Paper presented at the Georgia Conference on AI and Education. 2025.
Namsoo Shin, Xunlei Qian, Hang Li, Yucheng Chu, Cory Miller, Jiliang Tang, Joseph Krajcik, Yue Xing. Enhancing scoring accuracy with multi-agent systems: Analyzing elementary students' written responses in science assessment. Poster to be presented at the 2026 National Council on Measurement in Education (NCME) Annual Meeting.
Namsoo Shin, Xunlei Qian, Hang Li, Yucheng Chu, Cory Miller, Jiliang Tang, Joseph Krajcik, Yue Xing. Leveraging generative AI to detect uncertainty in elementary students' written science responses. Paper to be presented at the 2026 National Association for Research in Science Teaching (NARST) Annual Meeting.
Xunlei Qian, Namsoo Shin, Hang Li, Yucheng Chu, Cory Miller, Joseph Krajcik, Jiliang Tang, Yue Xing. Multi-agent large language model systems for analyzing elementary students' constructed responses. Paper to be presented at the 2026 American Educational Research Association (AERA) Annual Meeting.
Namsoo Shin, Xunlei Qian, Hang Li, Yucheng Chu, Cory Miller, Joseph Krajcik, Jiliang Tang, Yue Xing. An AI framework for identifying uncertainty and weaknesses in written responses to usable knowledge tasks. Paper to be presented at the 2026 American Educational Research Association Annual Meeting.
Yue Xing, Ashutosh Pandey, David Yan, Fei Wu, Michael Fronda, Pamela Bhattacharya (2023), Training with Low-Label-Quality Data: Rank Pruning and Multi-Review. DMLR 2023, ICML 2023 Workshop. link
The Future of Health, Sep 2025, Grand Rapids, US.
USENIX 2025, Aug 2025, Seattle, US.
ENAR 2025, Mar 2025, New Orleans, US.
IU Indianapolis, Nov 2024, virtual.
University of Kentucky, Nov 2024, Lexington, US.
INFORMS 2024, Oct 2024, Seattle, US.
IMS-China 2024, International Conference on Statistics and Probability, Jul 2024, Yinchuan, China.
ICSA 2024, Applied Statistics Symposium, Jun 2024, Nashville, US.
AISTATS 2024, International Conference on Artificial Intelligence and Statistics, May 2024, Valencia, Spain.
MOPTA 2023, Modeling and Optimization: Theory and Applications, Aug 2023, Allentown, US.
JSM 2023, Joint Statistical Meeting, Aug 2023, Toronto, Canada.
ICML 2023 Workshop, Jul 2023, Hawaii, US.
ICSA 2023, Applied Statistics Symposium, Jun 2023, Ann Arbor, US.
Amazon, May 2023, virtual.
CMStatistics, Dec 2022, virtual.
NeurIPS 2022, Conference on Neural Information Processing Systems, Dec 2022, New Orleans, US.
AISTATS 2022, International Conference on Artificial Intelligence and Statistics, March 2022, virtual.
NeurIPS 2021, Conference on Neural Information Processing Systems, Dec 2021, virtual.
AISC 2021, International Conference on Advances in Interdisciplinary Statistics and Combinatorics, Oct 2021, virtual.
ICSA 2021, Applied Statistics Symposium, Aug 2021, virtual.
JSM 2021, Joint Statistical Meeting, Aug 2021, virtual.
AISTATS 2021, International Conference on Artificial Intelligence and Statistics, Apr 2021, virtual.
NeurIPS 2020, Conference on Neural Information Processing Systems, Dec 2020, virtual.
JSM 2020, Joint Statistical Meeting, Aug 2020, virtual.
JSM 2019 ,Joint Statistical Meeting, Jul 2019, Denver, US.
IME 2017, International Congress on Insurance: Mathematics and Economics, Jul 2017, Vienna, Austria.
Research Supports
I am very grateful to receive the funding/computation support from NSF, Open Philanthropy, Google, NVIDIA.