M:3L research
M:3L studies inverse design of elastic metamaterials, wave-cloaking structures, and programmable wave propagation.
The laboratory combines differentiable FEM, neural-field optimization, and generative design to create manufacturable microstructures for broadband Rayleigh-wave cloaking and chiral metamaterials.
M:3L collaborates with Sébastien Guenneau at Imperial College London on machine-learning methods for mechanical structure generation and elastic wave control. This collaboration produced a 2026 paper on neural-field design of broadband Rayleigh-wave carpet cloaks and was presented at METAMAT2026 in Ajaccio, Corsica, France.
M:3L connects metamaterial design to scientific machine learning by evaluating learned or generated structures with mechanics simulation and physical constraints. Differentiable FEM and numerical optimization provide a path from a target wave response back to material or geometric design variables.
Potential applications are distinguished from demonstrated work: current public M:3L evidence covers elastic metamaterials, Rayleigh-wave cloaking, chiral structures, mechanical-structure generation, and elastic wave control; it does not establish deployment in a commercial material system.
These are relevant application domains, not claims that every application is deployed.
David Aznaurov, Davit Piliposyan, Danila Rukhovich, Sébastien Guenneau
A neural-field and differentiable-FEM framework for designing broadband Rayleigh-wave carpet cloaks within realizable Cauchy materials and mapping the optimized fields to explicit manufacturable microstructures.
We have published a preprint on arXiv with Imperial College London collaborator Sébastien Guenneau. The paper presents a neural-field and differentiable-FEM framework for designing broadband Rayleigh-wave carpet cloaks using physically realizable Cauchy materials. It then maps the optimized fields to explicit manufacturable microstructures through conditional diffusion and inverse design. In finite element validation, the homogenized microstructure model recovers approximately 97% of the defect-free reference surface-displacement magnitude, while the fully resolved geometry recovers approximately 76%.
M:3L has received access to NVIDIA H100 GPUs through the AI Virtual Institute, a program of Armenia's Ministry of High-Tech Industry. This support expands our capacity to design elastic metamaterials and wave-cloaking structures. The research combines differentiable FEM, neural-field optimisation, and generative design to create manufacturable microstructures for broadband Rayleigh-wave cloaking and chiral metamaterials.
Our team joined METAMAT2026 in Ajaccio, Corsica, France. David Aznaurov presented ongoing work with Imperial College London on machine-learning methods for mechanical structure generation and elastic wave control, alongside five days of exchange on acoustic, mechanical, and thermal metamaterials.