Research ThemesOur research explores the geometry of data and models across multiple areas. Graph Neural NetworksUnderstanding and improving GNNs through geometric perspectives, addressing over-smoothing, and developing novel architectures.
Geometric Deep LearningLeveraging hyperbolic and Riemannian geometry for better representation learning of hierarchical and structured data.
Trustworthy AIDeveloping methods for machine unlearning, privacy-preserving ML, and robust evaluation of AI systems.
ML for ScienceApplying machine learning to scientific discovery, including drug design, molecular modeling, and computational biology.
Language ModelsResearch on LLM personalization, retrieval-augmented generation, and geometric reasoning in vision-language models.
Generative ModelsAdvancing graph generation, diffusion models, and generative approaches for structured data.
|