Zhaogeng Liu

Title:Assistant Professor

Education:Jilin University

Email:liuzg25@jlu.edu.cn

Homepage:

Research Areas:LLM Fine-tuning、Spiking Neural Network、Graph Neural Network

About Me

ZhaogengLiu, Assistant Professor, PhD Supervisor at the School of Artificial Intelligence, Jilin University. He received his Ph.D. degree from the School of Artificial Intelligence, Jilin University in 2024, supervised by Prof. Yi Chang. His current research mainly focuses on large language model fine-tuning, spiking neural networks (SNNs), and graph neural networks (GNNs).


Research

[1] Hanyuan Zheng†, Haozhen Zhang†, Tianshuo Chen†,Zhaogeng Liu†, Yi Chang*, Bin Gu*. Distribution-Aware Multi-Granularity Phase Coding: Towards Lower Conversion Error for Spike-Driven Large Language Models. Accepted by International Conference on Learning Representations (ICLR 2026).

[2] Jia Zhang†, Yu Bai†, Hualin Zhang†, Tianshuo Chen†,Zhaogeng Liu†, Zhiqiang Xu, Yi Chang, Bin Gu*. Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes. Accepted by International Conference on Learning Representations (ICLR 2026).

[3]Zhaogeng Liu†, Haozhen Zhang†, Hualin Zhang, Xingchen Li, Wanli Shi, Bin Gu*, Yi Chang*. Query Efficient Black-Box Visual Prompting with Subspace Learning. Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR 2025): 4322-4331.

[4] Tianxing Man†, Xingchen Li†,Zhaogeng Liu†, Haozhen Zhang, Bin Gu*, Yi Chang*. Enhancing Black-Box Adversarial Attacks on Discrete Sequential Data via Bilevel Bayesian Optimization in Hybrid Spaces. Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD 2025): 1032-1043.

[5] Haozhen Zhang†,Zhaogeng Liu†, Bin Gu*, Yi Chang*. Leveraging First and Zeroth-Order Gradient to Address Imbalanced Black-Box Prompt Tuning via Minimax Optimization. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2025): 22407-22415.

[6]Zhaogeng Liu, Jielong Yang*, Xionghu Zhong, Wenwu Wang, Hechang Chen*, Yi Chang. A Novel Composite Graph Neural Network. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024, 35(10): 13411-13425.

[7]Zhaogeng Liu, Feng Ji*, Jielong Yang*, Xiaofeng Cao, Muhan Zhang, Hechang Chen*, Yi Chang*. Refining Euclidean Obfuscatory Nodes Helps: A Joint-Space Graph Learning Method for Graph Neural Networks. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2024, 35(9): 11720-11733.

[8]Zhaogeng Liu, Jielong Yang*, Li Wang, Yi Chang*. A Novel Relation Aware Wrapper Method for Feature Selection. Pattern Recognition, 2023, 140: 109566.

[9] Haotian Chi,Zhaogeng Liu, Xing Chen, Bohao Qu, Jifeng Hu, Yuan Jiang, Hechang Chen∗, Yi Chang. State Transition Difference Prediction for Deep Reinforcement Learning. Pattern Recognition, 2025: 112824.

[10] Shutong Zhang, Xing Chen,Zhaogeng Liu, Hechang Chen, Yi Chang*. HiPPO: Enhancing Proximal Policy Optimization with Highlight Replay. Pattern Recognition, 2025, 162: 111408.

return