1 citations · 1 across the 3 of their papers we have counts for
4 papers
Global Transport Couplings for Classifier-Free Guided Flows
Katarina Petrović, Zander W. Blasingame, Danyal Rehman +5
Optimal-transport couplings have been shown to reduce training variance in unconditional flow models, but their role in conditional generation remains unclear. A natural approach c…
Curly Flow Matching for Learning Non-gradient Field Dynamics
Katarina Petrović, Lazar Atanackovic, Viggo Moro +5
Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural sciences. Such models rely on key assumptions about t…
Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection
Jakob Shack, Katarina Petrovic, Olga Saukh
Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates t…
Temporal Graph Rewiring with Expander Graphs
Katarina Petrović, Shenyang Huang, Farimah Poursafaei +1
Evolving relations in real-world networks are often modelled by temporal graphs. Temporal Graph Neural Networks (TGNNs) emerged to model evolutionary behaviour of such graphs by le…