Scholar
Davide Buffelli
Google Scholar ID: v28My7wAAAAJ
AI Research Scientist at MediaTek Research
Citations & Impact
Citations
220
H-index
7
i10-index
6
Publications
17
Co-authors
20
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers including 'LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarsening' accepted at NeurIPS 2025 New Perspectives in Advancing Graph Machine Learning Workshop, 'CliquePH: Higher-Order Information for Graph Neural Networks through Persistent Homology on Clique Graphs' accepted at LoG 2024, 'Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization' and 'Deep Equilibrium Algorithmic Reasoning' both accepted at NeurIPS 2024, among others.
Research Experience
- Research Scientist Intern at Meta AI (London) and Samsung AI Research (Cambridge), and visiting student in Professor Pietro Liò's group at the University of Cambridge and Dr. Bastian Rieck's group at Helmholtz Munich.
Education
- Ph.D. in Information Engineering from the University of Padova, supervised by Professor Fabio Vandin, focusing on Graph Neural Networks and Graph Representation Learning.
Background
- Senior Deep Learning Researcher at MediaTek Research in London. Broad interest in Deep Learning, with a current focus on foundation models for multimodal time-series, optimization, and representation learning for structured data.
