Johannes Lutzeyer — accepted AI-conference papers

2026

GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation

Ye Zhu, Kaleb Newman, Johannes Lutzeyer, Adriana Romero-Soriano, Michal Drozdzal, Olga Russakovsky

ICML 2026poster

Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. This lack of diversity not only restricts user choice, but also risks amplifying societal biases. In this work, we enhance the T2I diversity through a geomet…

Cited by 0 Source ↗Scholar ↗

2023

Graph Ordering Attention Networks

Michail Chatzianastasis, Johannes Lutzeyer, George Dasoulas, Michalis Vazirgiannis

AAAI 2023technical

Graph Neural Networks (GNNs) have been successfully used in many problems involving graph-structured data, achieving state-of-the-art performance. GNNs typically employ a message-passing scheme, in which every node aggregates information from its neighbors using a permutation-invariant aggregation…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗