Profile Image

Hi I'm Zhenyu (Fischer) Lei

I'm a PhD student at the University of Virginia. My ultimate goal is to make AI systems more accessible . My current interests lie in:
  • Efficiency: Especially how to distill the whole ability of larger black-box (or white-box) models into smaller ones.
  • Reliability: How to make accessible models more reliable.
My current side projects include:
  • AI for Urban+Environment: How does AI helps in air quality and disaster mangement.
  • AI for Neuroscience: How to use AI to understand the brain.
I also have experience in solving real-world challenges with LLMs (ACL23, ACL25), graph models (ACL24, AAAI25), spatial-temporal models (AAAI25), AI for neuroscience (AAAI25), AI for biochemistry (Arxiv), and fairness algorithms (WWW24). If you are interested in my research, please feel free to reach out!

πŸ”₯What's New

πŸ“– Selected Publications (* indicates equal contribution)

2025

stfit diagram
ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data
Zhenyu Lei, Yushun Dong, Jundong Li, Chen Chen
AAAI 2025 (Oral)

In this paper, we study an under-explored research problem of inductive forecasting with limited training data, which requires models to generalize the learned spatial-temporal dependencies from the nodes with available training temporal data to those nodes without. To handle this problem, we propose ST-FiT that can achieve superior performance without additional fine-tuning.

brainmap diagram
BrainMAP: Learning Multiple Activation Pathways in Brain Networks
Song Wang*, Zhenyu Lei*, Zhen Tan, Jiaqi Ding, Xinyu Zhao, Yushun Dong, Guorong Wu, Tianlong Chen, Chen Chen, Aiying Zhang, Jundong Li
AAAI 2025 (Oral)

while significant progress has been made in understanding brain activity through functional connectivity (FC) graphs, challenges remain in effectively capturing and interpreting the complex, long-range dependencies and multiple pathways that are inherent in these graphs. In this work, we introduce BrainMAP, a novel framework that can extract multiple long-range activation pathways with adaptive sequentialization and pathway aggregation.

2023

brainmap diagram
BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency
Zhenyu Lei*, Herun Wan*, Wenqian Zhang, Shangbin Feng, Jundong Li, Qinghua Zheng, Minnan Luo,
ACL 2023

we proposed a bot-detection model named BIC. BIC interacts and exchanges information across text modality and graph modality by a text-graph interaction module. BIC contains a semantic consistency module that derives the inconsistency from tweets by the attention weight to identify advanced bots.

βš™οΈ Industrial Experience

AT&T
2025.06 – 2025.8
Applied Scientist Intern @ Bedminister
Host: Dr. Qiong Wu Β· Bedminister, NJ

πŸ§‘β€πŸŽ“ Education

University of Virginia
2023.08 – present
Ph.D. in Electrical and Computer Engineering
Advisor: Prof. Jundong Li
Xi'an Jiaotong University
2019.08 – 2023.07
B.S. in Physics (Honor)
GPA: 89.5 / 100.0
Advisor: Prof. Minnan Luo

πŸ‘· Service

🏊 Miscellaneous

Credits goes to Zhaoxuan Tan and CommunityPro!