collaborators

7 papers

cs.LG2026

Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems

Fleur Hendriks, Ondřej Rokoš, Martin Doškář +2

Bifurcation phenomena in nonlinear dynamical systems often lead to multiple coexisting stable solutions, particularly in the presence of symmetry breaking. Deterministic machine le…

cs.LG2026

Auto-Regressive U-Net for Full-Field Prediction of Shrinkage-Induced Damage in Concrete

Liya Gaynutdinova, Petr Havlásek, Ondřej Rokoš +2

This paper introduces a deep learning approach for predicting time-dependent full-field damage in concrete. The study uses an auto-regressive U-Net model to predict the evolution o…

cs.LG2026

Homogenization with Guaranteed Bounds via Primal-Dual Physically Informed Neural Networks

Liya Gaynutdinova, Martin Doškář, Ondřej Rokoš +1

Physics-informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs) relevant to multiscale modeling, but they often fail when applied to ma…

physics.app-ph2025

Non-uniform pneumatic actuation switches macroscopic properties of elastomeric honeycombs

Ondřej Faltus, Martin Doškář, Jan Havelka +2

Honeycomb microstructures with circular voids are well known to undergo pattern transformations under macroscopic strain loading. Depending on the biaxiality of the applied strain,…

cond-mat.soft2025

Wallpaper Group-Based Mechanical Metamaterials: Dataset Including Mechanical Responses

Fleur Hendriks, Vlado Menkovski, Martin Doškář +3

Mechanical metamaterials often exhibit pattern transformations through instabilities, enabling applications in, e.g., soft robotics, sound reduction, and biomedicine. These transfo…

cond-mat.soft2025

Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials

Fleur Hendriks, Vlado Menkovski, Martin Doškář +2

Soft, porous mechanical metamaterials exhibit pattern transformations that may have important applications in soft robotics, sound reduction and biomedicine. To design these innova…