Vlado Menkovski
Papers
2
Total Citations
8
H-Index
2
About
Vlado Menkovski is a leading researcher at the intersection of geometric deep learning and computational mechanics, with a primary focus on mechanical metamaterials and homogenization. His work addresses the critical challenge of accurately and rapidly simulating soft, porous metamaterials—materials whose pattern transformations hold promise for applications in soft robotics, sound reduction, and biomedicine. Menkovski’s major contribution lies in pioneering symmetry-aware machine learning models, most notably the *Similarity Equivariant Graph Neural Networks* for homogenization, which leverage the inherent symmetries in metamaterial microstructures to dramatically improve simulation fidelity. This work, already garnering 6 citations since 2025, demonstrates his ability to bridge abstract mathematical principles with tangible engineering problems. He further advanced the field by curating the *Wallpaper Group-Based Mechanical Metamaterials* dataset, a foundational resource that systematically links mechanical responses to the 17 wallpaper symmetry groups. This dataset enables data-driven discovery of structure-property relationships in materials that undergo instability-driven pattern transformations. Through these contributions, Menkovski is establishing a new paradigm for designing next-generation programmable materials.
Research Focus
Key Achievements
Top Papers
- 1
- 2