Guangyu Meng

PhD Candidate in Computer Science | University of Notre Dame

About Me

I am a PhD candidate in Computer Science at the University of Notre Dame, working under the supervision of Prof. Erin W. Chambers and Prof. Danny Z. Chen. My research integrates topological data analysis (TDA) with deep learning for medical image analysis, organized around three themes: (1) embedding persistent homology into self-supervised and unsupervised learning for structurally aware representations, (2) building scalable computational infrastructure including GPU-accelerated persistent homology and optimal transport-based comparison of topological summaries, and (3) combining neural networks with symbolic reasoning via LLM-based agentic frameworks for automated topological analysis. I also develop curriculum learning methods for efficient LLM fine-tuning. My long-term goal is trustworthy, auditable AI that characterizes biological structure from cells to whole organisms.

Research Interests

• Topological Data Analysis for Medical Image Analysis
• Self-Supervised and Unsupervised Deep Learning
• GPU-Accelerated Topological Computation
• Optimal Transport and Computational Geometry
• LLM-Based Agentic Frameworks and Neuro-Symbolic Reasoning
• Curriculum Learning for Large Language Models