3 papers
cs.LG2026
CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching
Marcel Musiałek, Iga Wolanin, Damian Ryczko +2
Complex-valued signals like MRI and audio spectrograms are typically modelled as flat two-channel Euclidean data. The inherited Euclidean metric vanishes at the o…
cs.LG2026
CEL: Comprehensive Counterfactual Explanations Library and Benchmark
Oleksii Furman, Łukasz Lenkiewicz, Marcel Musiałek +1
Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's predict…
cs.CV2026
Open-Set Vein Biometric Recognition with Deep Metric Learning
Paweł Pilarek, Marcel Musiałek, Anna Górska
Most state-of-the-art vein recognition methods rely on closed-set classification, which inherently limits their scalability and prevents the adaptive enrollment of new users withou…