Haggai Maron
Scholar

Haggai Maron

Google Scholar ID: 4v8uJrIAAAAJ
Assistant Professor at the Technion, Research Scientist at NVIDIA Research
Graph Neural NetworksGeometric Deep LearningDeep LearningEquivariant Architectures
Citations & Impact
All-time
Citations
6,519
 
H-index
30
 
i10-index
46
 
Publications
20
 
Co-authors
38
list available
Resume (English only)
Academic Achievements
  • ICML 2020 paper 'On Learning Sets of Symmetric Elements' received the Outstanding Paper Award
  • Recipient of the Alon scholarship for the Integration of Outstanding Faculty
  • Served as Area Chair for NeurIPS 2023
  • Delivered tutorials at Simons Institute and Learning on Graphs Conference on topics including 'The expressive power of GNNs' and 'Equivariant architectures for learning in deep weight spaces'
  • Oral presentation at LOG 2025: 'GL Equivariant Metanetworks for Learning on Low Rank Weight Spaces'
Background
  • Assistant Professor and Robert J. Shillman Fellow at the Faculty of Electrical and Computer Engineering, Technion
  • Senior Research Scientist at NVIDIA Research, Tel Aviv lab
  • Primary research interest: machine learning, especially deep learning for structured data
  • Focuses on applying deep learning to sets, graphs, point clouds, surfaces, weight spaces, and other mathematical objects with inherent symmetry
  • Research goals: (1) theoretically understand and design deep learning architectures (e.g., expressive power); (2) demonstrate practical effectiveness on real-world structured data problems