About
I am a PhD student at the Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University (PolyU), advised by Prof. Jibin Wu and Prof. Kay Chen Tan. I also work closely with Prof. Yujie Wu and Prof. Guozhang Chen.
Prior to this, I obtained my M.Eng. degree in Biomedical Engineering from the Southern University of Science and Technology (SUSTech) in 2023, advised by Prof. Quanying Liu. Before that, I received my B.Eng. degree in Computer Science and Engineering from SUSTech in 2020, working with Prof. Jialin Liu and Prof. Xin Yao.
My current research mainly focuses on AI for Neuroscience and LLM. I have led first-author research published at ICLR, ICML, NeurIPS, Human Brain Mapping and TEVC, and have also contributed as a co-author to works appearing at ACM MM and ICASSP.
I serve as a reviewer for several top journals (TMLR, TNNLS, TCDS) and top conferences (NeurIPS, ICLR, CVPR, KDD, ACM MM, ACM TheWebConf).
I am expected to graduate in 2027.6, and I am currently seeking opportunities through talent programs in the 2026 Fall recruitment cycle. Please feel free to contact me via email: ziyuanye9801@gmail.com
Selected Publications
View All →Discovering heterogeneous synaptic plasticity rules via large-scale neural evolution
Ziyuan Ye†, Beichen Huang†, Yujie Wu, Guozhang Chen, Jibin Wu (equal contribution)†
International Conference on Learning Representations (ICLR), 2026
A computational framework that leverages Darwinian evolutionary principles to discover biologically plausible, heterogeneous synaptic plasticity rules in a realistic model of the mouse primary visual cortex, revealing diverse families of high-performing plasticity rules and their implications for learning and memory.
KoopSTD: reliable similarity analysis between dynamical systems via approximating Koopman spectrum with timescale decoupling
Shimin Zhang†, Ziyuan Ye†, Yinsong Yan, Zeyang Song, Yujie Wu, Jibin Wu (equal contribution)†
International Conference on Machine Learning (ICML), 2025
A metric for measuring dynamical similarity between (neural/dynamical) systems by approximating the Koopman spectrum with timescale decoupling and spectral residual control.
SAME: Uncovering GNN black box with structure-aware shapley-based multipiece explanations
Ziyuan Ye†, Rihan Huang†, Qilin Wu, Quanying Liu (equal contribution)†
Advances in Neural Information Processing Systems (NeurIPS), 2023
A post-hoc explanation method for graph neural networks (GNNs) that uncovers structure-aware feature interactions using a Shapley-based multipiece explanation approach.
Explainable fMRI-based brain decoding via spatial temporal-pyramid graph convolutional network
Ziyuan Ye, Youzhi Qu, Zhichao Liang, Mo Wang, Quanying Liu
Human Brain Mapping, 2023
A biologically inspired architecture, Spatial Temporal-pyramid Graph Convolutional Network (STpGCN), to capture the spatial–temporal graph representation of functional brain activities for explainable fMRI-based brain decoding.