3 papers
cs.LG2026
Grounding Functional Similarity by Invariance-Aware Model Stitching
Ioannis Athanasiadis, Anmar Karmush, Michael Felsberg
In deep learning, functional similarity evaluation quantifies the extent to which independently trained models learn similar input--output relationships. In model stitching, functi…
cond-mat.mtrl-sci2026
Benchmark Dataset for Catalysis on 2D MXenes
Pavlo Melnyk, Anmar Karmush, Mårten Wadenbäck +4
Merging first-principles calculations with machine learning (ML), we aim to accelerate the exploration of catalytic behaviour in novel materials. We focus on two-dimensional (2D) T…
cs.LG2026
Generating Symmetric Materials using Latent Flow Matching
Anmar Karmush, Cedric Mathieu Brandenburg, Soheil Ershadrad +3
Tackling the task of materials generation, we aim to enhance the previously proposed All-atom Diffusion Transformer (ADiT) by introducing SymADiT, a symmetry-aware variant. To do s…