Welcome to Hong Xie's Homepage

Hong Xie Research professor State Key Laboratory of Cognitive Intelligence Anhui Province Key Laboratory of Big Data Analysis and Application (BDAA) School of Computer Science and Technology University of Science and Technology of China (USTC) Email: xiehong2018@foxmail.com

Biography:

Hong Xie is currently a research professor at School of Computer Science and Technology, University of Science and Technology of China (USTC) . He is a member of Prof. Enhong Chen's research group. He received Ph.D. degree in the Department of Computer Science and Engineering at The Chinese University of Hong Kong (CUHK) in 2015, proudly under the supervision of Prof. John C.S. Lui. He received his B.Eng. degree from the School of Computer Science and Technology at USTC in 2010. Hong Xie was a postdoctoral research fellow at Department of Computing Science and Engineering, CUHK hosted by Prof. John C.S. Lui, and a postdoctoral research fellow at School of Computing, Nationial University of Singapore hosted by Prof. Richard T.B. Ma . He was also a faculty member at Chongqing University. He is a member of CCF, a member of IEEE and a member of ACM. At spare time, he enjoys playing table tennis, badminton, basketball, etc.

Research Interests

• Bandits and reinforcement learning, with a special focus on the large scale setting.
• LLM, with a special focus on reinforcement fine-tuning and agent.

Recent Works ( full list )

• Wei Yang, Hong Xie, Tao Tan, Xin Li, Defu Lian, Enhong Chen
Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance.
Preprint, 2026.
• Hong Xie, Xiao Hu, Tao Tan, Haoran Gu, Xin Li, Jianyu Han, Defu Lian, Enhong Chen
Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective.
Preprint, 2026.
• Xiao Hu, Hong Xie, Tao Tan, Defu Lian, Jianyu Han
Rethinking Reinforcement Fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective.
Preprint, 2026.
• Hantao Yang, Hong Xie, Defu Lian, Enhong Chen
LLM Cache Bandit Revisited: Addressing Query Heterogeneity for Cost-Effective LLM Inference.
Preprint, 2025.
• Xu Huang, Yuefeng Huang, Weiwen Liu, Xingshan Zeng, Yasheng Wang, Ruiming Tang, Hong Xie, Defu Lian
Advancing and Benchmarking Personalized Tool Invocation for LLMs.
Preprint, 2025.
• Cheng He, Xu Huang, Gangwei Jiang, Zhaoyi Li, Defu Lian*, Hong Xie*, Enhong Chen, Xijie Liang, Zhengzengrong, Patrick Lee
GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data.
The Fourteenth International Conference on Learning Representations ( ICLR ), 2026.
• Hongyi Xie, Min Zhou*, Qiao Yu, jialiang Yu, Zhenli sheng, Hong Xie*, Defu Lian
M2-MFP: A Multi-Scale and Multi-Level Memory Failure Prediction Framework for ReliableCloud Infrastructure
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), applied data science track, Artifact Badge Award, 2025.
• Weidong Wu, Qinlin Zhao, Hao Chen, Lexin Zhou, Defu Lian, Hong Xie
Exploring the Choice Behavior of Large Language Models
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025.
• Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying Wei
Understanding and Patching Compositional Reasoning in LLMs
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2024.
• Xiaoying Zhang, Junpu Chen, Hongning Wang, Hong Xie, Yang Liu, John C.S. Lui, Hang Li
Uncertainty-Aware Instance Reweighting for Off-Policy Learning
Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.
• Liming Wang, Hong Xie*, Ye Li, Jian Tan, John C.S. Lui.
Interactive Log Parsing via Light-weight Feedback
The Web Conference (WWW) , 2023.

• Mingze Zhong, Hong Xie*, Qingsheng Zhu.
Quantifying Assimilate-Contrast Effects in Online Rating Systems: Modeling, Analysis and Application.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) , 2021.
• Tingwei Liu, Hong Xie*, and John C.S. Lui.
``Optimizing Mixture Importance Sampling Via Online Learning: Algorithms and Applications. '' 
International Conference on Computer Communication (INFOCOM) , 2020.
(Best Paper Candidate)
• Hong Xie, Mingze Zhong, Xiaoyu Shi, Xiaoying Zhang, Jiang Zhong, Mingsheng Shang 
``Probabilistic Modeling of Assimilate-ContrastEffects in Online Rating Systems.''
IEEE Transactions on Knowledge and Data Engineering (TKDE), 36(2): 795-808, 2024 .
• Hong Xie, Pei Yi, Yongkun Li and John C.S. Lui 
``Optimizing Random Walk Based Statistical Estimation over Graphs via Bootstrapping.''
IEEE Transactions on Knowledge and Data Engineering (TKDE) , 35(3), 2916-2929, 2023.
• Ye Li, Hong Xie*, Yishi Lin and John C.S. Lui
``Rewarding Social Recommendation in OSNs: Empirical Evidences, Modeling and Optimizations.''
IEEE Transactions on Knowledge and Data Engineering (TKDE) , vol 34(9), 4410-4424, 2022.

Teaching

• 2021 Fall semester: Fundamentals of Machine Learning

Honors

• Best paper candidate, IEEE INFOCOM, 2020
• One paper fast tracked to IEEE Trans. on Mobile Computing, 2020
• Chongqing Talents: Exceptional Young Talents, 2020
• First class prize in Chongqing Science and Technology Progress(10/15),2020

Professional Services

• 2025: AAAI(TPC), IJCAI(TPC), AISTATS(TPC), ICML(TPC), ICLR(Rev.), KDD(Rev., Excellent reviewer)
• 2024: AAAI(TPC), IJCAI(TPC), AISTATS(TPC), ICML(TPC), NeurIPS(TPC), ICLR(REV), WWW(Rev.), KDD(Rev.)
• 2023: AAAI(TPC), IJCAI(TPC), AISTATS(TPC), ICML(TPC), NeurIPS(TPC), ECML-PKDD(TPC)
• 2022: AAAI(TPC), IJCAI(TPC), AISTATS(REV), ICML(TPC), NeurIPS(TPC, top reviewer)
• 2021: AAAI(TPC)
• 2019: IEEE ASONAM (IT TPC)
• 2018: IEEE ASONAM (IT TPC)

• IEEE/ACM Transactions on Networking
• IEEE Transactions on Mobile Computing
• IEEE Transactions on Services Computing
• IEEE Transactions on Network Science and Engineering
• Elsevier Performance Evaluation Journal
• ACM Transactions on Modeling and Performance Evaluation of Computing Systems