I am a second-year Ph.D. student in the College of Computer Science and Technology at Zhejiang University, where I am advised by Prof. Yang Yang. I completed my undergraduate studies at the ZJU-UIUC Institute, majoring in Computer Engineering (CompE), and earned dual bachelor’s degrees in engineering from Zhejiang University and The Grainger College of Engineering at the University of Illinois Urbana-Champaign (UIUC). In 2022, I also joined an exchange program at UIUC. My research interests include neural signal decoding, large-scale models for EEG signals, machine learning for healthcare, and human-centered AI. Here is my CV (English version / Chinese version).
🔥 News
-
[Jan. 2026]: 🎉🎉 BrainMosaic was accepted to ICLR 2026.
-
[Oct. 2025]: 🎉🎉 Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics was accepted by IEEE RBME.
-
[Sept. 2024]: 🎉🎉 Con4m was accepted to NeurIPS 2024.
📝 Publications
Neural Semantic Decoding
Assembling the Mind’s Mosaic: Towards EEG Semantic Intent Decoding
Jiahe Li, Junru Chen, Fanqi Shen, Jialan Yang, Jada Li, Zhizhang Yuan, Baowen Cheng, Meng Li, Yang Yang
BrainMosaic introduces Semantic Intent Decoding (SID), a novel framework that translates EEG/SEEG signals into natural language by representing meaning as flexible, compositional semantic units. By aligning neural representations with a continuous semantic space and leveraging LLMs for reconstruction, it enables interpretable, open-vocabulary BCI communication.
Deep Learning for EEG/iEEG-Based Neurological Diagnostics
Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics
Jiahe Li, Xin Chen, Fanqi Shen, Junru Chen, Yuxin Liu, Daoze Zhang, Zhizhang Yuan, Fang Zhao, Meng Li, Yang Yang
This review provides a comprehensive overview of recent advances in deep learning for EEG and iEEG analysis in neurological disorder diagnosis, summarizing trends across 46 datasets and 7 conditions while proposing a standardized benchmark for future research.
Brain Signals Modeling
Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification
Junru Chen, Tianyu Cao, Jing Xu, Jiahe Li, Zhilong Chen, Tao Xiao, Yang Yang
Con4m is a consistency-learning framework that effectively leverages contextual information to better distinguish consecutive segments in segmented time-series classification tasks, while also harmonizing inconsistent boundary labels during training.
Dynamic Network Embedding
Fast Updating Truncated SVD for Representation Learning with Sparse Matrices
Haoran Deng, Yang Yang, Jiahe Li, Cheng Chen, Weihao Jiang, and Shiliang Pu
Code
This work aims to develop a more efficient method for dynamically updating truncated Singular Value Decomposition (SVD) for sparse, evolving matrices while maintaining high precision.
Accelerating Dynamic Network Embedding with Billions of Parameter Updates to Milliseconds
Haoran Deng, Yang Yang, Jiahe Li, Haoyang Cai, Shiliang Pu, and Weihao Jiang
The DAMF algorithm enables efficient and accurate dynamic network embedding by updating billion-edge graphs in under 10 milliseconds while capturing higher-order neighborhood information.
🎖 Honors and Awards
- 2021, 2023 National Scholarship of China
- 2021, 2022 Outstanding student association leader of Zhejiang University
- 2022 Zhejiang Provincial Government Scholarship
- 2023 Five-Star Volunteer of Zhejiang University
- 2024 Outstanding Graduate of Zhejiang Province
- 2024 Outstanding Graduate of Zhejiang University
- 2025 Outstanding Graduate Student of Zhejiang University
- 2025 Outstanding Graduate Student Leader of Zhejiang University
📖 Education
- 2024.09 - Present, Ph.D. student in Computer Science, Zhejiang University.
- 2020.09 - 2024.06, Dual bachelor’s degrees in engineering from Zhejiang University and The Grainger College of Engineering at the University of Illinois Urbana-Champaign (UIUC).
- 2017.09 - 2020.07, Shandong Experimental High School.
🍑 Personal
Room78
I co-founded the Room78 Algorithm Club in 2020 at ZJU’s Haining Campus and served as its president until September 2022. We built and maintain our own online judge system, which is used for daily training, practice, and small-scale simulation contests. Room78 also organizes workshops on research and competition experience sharing, as well as algorithm lectures such as “Our Life Dominated by Algorithms” for students on the Haining campus.
Tuxun
I also enjoy playing Tuxun, a geography-guessing game similar to GeoGuessr. My Tuxun profile is mainly focused on locations in China, and I reached the top 8 in the Fourth Tuxun Intercollegiate Competition.
Field scene: Cao Guangbiao High-Tech Building, Yuquan Campus, Zhejiang University