Selected peer-reviewed and accepted work. My name is shown in bold.
2027
WACV
A Stochastic Latent Variable Generalization of Joint-Embedding Predictive Architectures
N. Giakoumoglou, P. Giakoumoglou, T. Stathaki
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2027
arXiv
Code
WACV
Generalizable AI-Generated Image Detection with Embedding-Space Explanations
N. Giakoumoglou, P. Giakoumoglou, T. Stathaki, S. Papadopoulos
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2027
arXiv
Code
2026
TIST
Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations
P. Giakoumoglou, M. Schinas, S. Papadopoulos
ACM Transactions on Intelligent Systems and Technology, accepted for publication, 2026
ACCV
What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?
N. Giakoumoglou, P. Giakoumoglou, A. Floros, K. M. Papadopoulos, T. Stathaki
Asian Conference on Computer Vision (ACCV), 2026
ACCV
ECCV
Three Necessary Principles for Self-Supervised Visual Representation Learning
N. Giakoumoglou, P. Giakoumoglou, T. Stathaki
ECCV Workshop on Unified World Models (UniWorld), 2026
arXiv
CVPRW
DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization
P. Giakoumoglou, S. Papadopoulos
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (AIMS), 2026
Paper
arXiv
Code
JIS
TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark
H. Mareen, D. Karageorgiou, P. Giakoumoglou, P. Lambert, S. Papadopoulos, G. Van Wallendael
Journal on Information Security, 2026
Paper
arXiv