Xiongxiao Xu
 |
Ph.D. Candidate |
About me
I am a Ph.D. candidate in the Department of Computer Science at Illinois Institute of Technology since Spring 2022, advised by Dr. Kai Shu. My research interests lie in sequential machine learning, such as LLMs, time series analysis, sequential recommendation and decision-making. I also have research experiences on GNNs, multi-armed bandits (RL), and their applications in anomaly detection, recommender system, and HPC.
I have several internship experience at leading tech companies and U.S. national laboratories. I worked at Amazon as an Applied Scientist Intern (Fall 2025), at TikTok as a Machine Learning Scientist intern (Summer 2025), and at Argonne National Laboratory as a Research Intern (Summer 2024). I received my B.S. degree in Computer Science from Chongqing University in 2020, advised by Dr. Hong Xie.Publications
Can Multimodal LLMs Perform Time Series Anomaly Detection? [arxiv][Code][Website]
Xiongxiao Xu, Haoran Wang, Yueqing Liang, Philip S. Yu, Yue Zhao, Kai Shu
Proceedings of the ACM on Web Conference (WWW), 2026Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach [arxiv][Code]
Xiongxiao Xu, Solomon Abera Bekele, Brice Videau, Kai Shu
Proceedings of the ACM on Web Conference (WWW), 2026 (Work done when interning at Argonne National Lab)Can Editing LLMs Inject Harm? [arxiv]
Canyu Chen, Baixiang Huang, Zekun Li, Zhaorun Chen, Shiyang Lai, Xiongxiao Xu, Jia-Chen Gu, Jindong Gu, Huaxiu Yao, Chaowei Xiao, Xifeng Yan, William Yang Wang, Philip Torr, Dawn Song, Kai Shu
Proceedings of The 40th AAAI Conference on Artificial Intelligence (AAAI), 2026Benchmarking LLMs for Political Science: A United Nations Perspective [arxiv]
Yueqing Liang, Liangwei Yang, Chen Wang, Congying Xia, Rui Meng, Xiongxiao Xu, Haoran Wang, Ali Payani, Kai Shu
Proceedings of The 40th AAAI Conference on Artificial Intelligence (AAAI), 2026SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting [arxiv][Code]
Xiongxiao Xu, Canyu Chen, Yueqing Liang, Baixiang Huang, Guangji Bai, Liang Zhao, Kai Shu
The 34th Conference on Information and Knowledge Management (CIKM), 2025Can Knowledge Editing Really Correct Hallucinations? [arxiv]
Baixiang Huang, Canyu Chen, Xiongxiao Xu, Ali Payani, Kai Shu
The 13th International Conference on Learning Representations (ICLR), 2025Piecing It All Together: Verifying Multi-Hop Multimodal Claims [arxiv]
Haoran Wang, Aman Rangapur, Xiongxiao Xu, Yueqing Liang, Haroon Gharwi, Carl Yang, Kai Shu
The 31st International Conference on Computational Linguistics (COLING), 2025Taxonomy-Guided Zero-Shot Recommendations with LLMs [arxiv]
Yueqing Liang, Liangwei Yang, Chen Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu
The 31st International Conference on Computational Linguistics (COLING), 2025Beyond Numbers: A Survey of Time Series Analysis in the Era of Multimodal LLMs [paper][techrxiv][Github][Website]
Xiongxiao Xu, Yue Zhao, Philip S. Yu, Kai Shu
techrxiv, 2025Beyond tokens: A survey on decoding methods for large language models and large vision-language models [paper][techrxiv]
Haoran Wang, Xiongxiao Xu, Philip S. Yu, Kai Shu
techrxiv, 2025Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation [arxiv]
Haoran Wang, Xiongxiao Xu, Baixiang Huang, Kai Shu
arxiv, 2025MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detection [Paper][Code]
Xiongxiao Xu, Kaize Ding, Canyu Chen, Kai Shu
Proceedings of The 11th IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2024Surrogate Modeling for HPC Application Iteration Times Forecasting with Network Features [Paper]
Xiongxiao Xu, Kevin A. Brown, Tanwi Mallick, Xin Wang, Elkin Cruz-Camacho, Robert B. Ross, Christopher D. Carothers, Zhiling Lan, Kai Shu
Proceedings of The ACM SIGSIM International Conference on Principles of Advanced Discrete Simulation (SIGSIM-PADS), 2024Hybrid PDES Simulation of HPC Networks using Zombie Packets [Paper]
Elkin Cruz-Camacho, Kevin A. Brown, Xin Wang, Xiongxiao Xu, Kai Shu, Zhiling Lan, Robert B. Ross, Christopher D. Carothers
ACM Transactions on Modeling and Computer Simulation (TOMACS), 2024Machine Learning for Interconnect Network Traffic Forecasting: Investigation and Exploitation [Paper]
Xiongxiao Xu, Xin Wang, Elkin Cruz-Camacho, Christopher D. Carothers, Kevin A. Brown, Robert B. Ross, Zhiling Lan, Kai Shu
Proceedings of The ACM SIGSIM International Conference on Principles of Advanced Discrete Simulation (SIGSIM-PADS), 2023Hybrid PDES Simulation of HPC Networks using Zombie Packets [Paper]
Elkin Cruz-Camacho, Kevin A. Brown, Xin Wang, Xiongxiao Xu, Kai Shu, Zhiling Lan, Robert B. Ross, Christopher D. Carothers
Proceedings of The ACM SIGSIM International Conference on Principles of Advanced Discrete Simulation (SIGSIM-PADS), 2023 (Best Short Paper Award)When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes [arxiv]
Canyu Chen, Yueqing Liang, Xiongxiao Xu, Shangyu Xie, Ashish Kundu, Ali Payani, Yuan Hong, Kai Shu
the workshop on Trustworthy and Socially Responsible Machine Learning (TSRML) at NeurIPS 2022Generalized Contextual Bandits With Latent Features: Algorithms and Applications [Paper][Supplementary]
Xiongxiao Xu, Hong Xie, John C.S. Lui
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021 (Work done as an undergraduate student)
Internships
Applied Scientist Intern, Amazon, Fall, 2025
Machine Learning Scientist Intern, TikTok, Summer, 2025
Research Intern, Argonne National Laboratory, Summer, 2024
Awards
Starr-Fieldhouse Research Fellowship Award, 2024
IEEE DSAA Student Travel Award, 2024
ACM SIGSIGM-PADS Student Travel Award, 2023, 2024
Best Short Paper Award, ACM SIGSIGM-PADS, 2023
Academic Services
Program Committee/Reviewer
The Association for Computational Linguistics Rolling Review (ACL ARR'25 Feb, May, July)
The Conference on Neural Information Processing Systems (NeurIPS'25)
The International Conference on Learning Representations (ICLR'25)
The AAAI Conference on Artificial Intelligence (AAAI’24, AAAI'25, AAAI'26)
The International Conference on Database Systems for Advanced Applications (DASFAA’24, DASFAA’25)
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)