Scholar
Shengyao Lu
Google Scholar ID: MSsab9EAAAAJ
Assistant Professor, University of Victoria
Citations & Impact
Citations
48
H-index
4
i10-index
2
Publications
9
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Selected publications include: 'TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution' (COLING 2025); 'EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time' (ICML 2024); 'Building Optimal Neural Architectures using Interpretable Knowledge' (CVPR 2024); 'GOAt: Explaining Graph Neural Networks via Graph Output Attribution' (ICLR 2024).
Research Experience
- Looking for highly motivated students starting in Fall 2026, especially those with backgrounds in LLM fine-tuning, visual-language alignment, and graph-language alignment.
Education
- Received BSc. and Ph.D. degrees from the University of Alberta.
Background
- Research interests: Graph-language alignment, Interpretability, Systematicity, Reasoning, GNNs, LLMs. Introduction: Shengyao Lu is an Assistant Professor in the Department of Computer Science (CS) at the University of Victoria (UVic). Her research primarily focuses on Explainable AI (XAI), graph neural networks (GNNs) and graph representation learning, reinforcement learning (RL) for reasoning, large language models (LLMs) toward artificial general intelligence (AGI).
