Selected Publications

On the Anisotropy of Score-Based Generative Models
Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
43rd International Conference on Machine Learning (ICML) 2026 [Gold Reviewer]

Expert Clustering and Knowledge Transfer for Whole Slide Image Classification
Kleanthis Marios Papadopoulos, Nikolaos Giakoumoglou, Andreas Floros, et al.
IEEE 23rd International Symposium on Biomedical Imaging (ISBI) 2026 [Oral] & MedEurIPS Workshop

Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution
Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
39th Annual Conference on Neural Information Processing Systems (NeurIPS) 2025 [Scholar Award]

Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Negatives
Nikolaos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos, Tania Stathaki
ICCV Workshop on Learning with Limited Resources & CVPR Second Workshop on Visual Concepts 2025

Trustworthy Image Super-Resolution via Generative Pseudoinverse
Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
ICLR Workshop on Deep Generative Models in Machine Learning: Theory, Principle and Efficacy 2025

INDigo: An INN-Guided Probabilistic Diffusion Algorithm for Inverse Problems
Di You, Andreas Floros, Pier Luigi Dragotti
IEEE 25th International Workshop on Multimedia Signal Processing (MMSP) 2023 [Best Paper Award]

Wavelet-Inspired Invertible Neural Networks for Image Modelling and Approximation
Andreas Floros
Master’s Thesis at Imperial College London 2022