755 citations · 1.4k across the 26 of their papers we have counts for
28 papers
Air Quality Downscaling with Station-Guided Pseudo-Supervision
Guorun Wang, Simone Foti, Andreas D. Demou +5
Super-resolving coarse atmospheric fields to local PM variations is uniquely challenged by a mismatch in spatial support: while pixels represent regional averages, ground-t…
Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
Panagiotis Koromilas, Theodoros Giannakopoulos, Mihalis A. Nicolaou +1
Supervised classification has a theoretical optimum, Neural Collapse (NC), yet neither of its two dominant paradigms reaches it in practice. Cross entropy (CE) leaves radial degree…
fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery
Andreas D. Demou, Panagiotis Koromilas, James Oldfield +2
Many features in pretrained Transformers span multiple layers: they emerge through stages of inference, persist in the residual stream, or are built jointly by parallel MLPs. Cross…
On the hydrodynamic behaviour of the immersed boundary -- lattice Boltzmann method for wetting problems
Elisa Bellantoni, Fabio Guglietta, Andreas Demou +6
We study the hydrodynamic behaviour of a mesoscale numerical model for wetting dynamics based on the immersed boundary - lattice Boltzmann (IBLB) method. This IBLB model features a…
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
Panagiotis Koromilas, Andreas D. Demou, James Oldfield +2
Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine a…
Environment-Aware Satellite Image Generation with Diffusion Models
Nikos Kostagiolas, Pantelis Georgiades, Yannis Panagakis +1
Diffusion-based foundation models have recently garnered much attention in the field of generative modeling due to their ability to generate images of high quality and fidelity. Al…
A Principled Framework for Multi-View Contrastive Learning
Panagiotis Koromilas, Efthymios Georgiou, Giorgos Bouritsas +3
Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentation…
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
James Oldfield, Shawn Im, Sharon Li +3
Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods le…
Immersed boundary - lattice Boltzmann method for wetting problems
Elisa Bellantoni, Fabio Guglietta, Francesca Pelusi +5
We develop a mesoscale computational model to describe the interaction of a droplet with a solid. The model is based on the hybrid combination of the immersed boundary and the latt…
Enabling Local Editing in Diffusion Models by Joint and Individual Component Analysis
Theodoros Kouzelis, Manos Plitsis, Mihalis A. Nicolaou +1
Recent advances in Diffusion Models (DMs) have led to significant progress in visual synthesis and editing tasks, establishing them as a strong competitor to Generative Adversarial…
Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
Panagiotis Koromilas, Giorgos Bouritsas, Theodoros Giannakopoulos +2
What do different contrastive learning (CL) losses actually optimize for? Although multiple CL methods have demonstrated remarkable representation learning capabilities, the differ…
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos +5
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, a…
Locality-preserving Directions for Interpreting the Latent Space of Satellite Image GANs
Georgia Kourmouli, Nikos Kostagiolas, Yannis Panagakis +1
We present a locality-aware method for interpreting the latent space of wavelet-based Generative Adversarial Networks (GANs), that can well capture the large spatial and spectral v…
Parts of Speech-Grounded Subspaces in Vision-Language Models
James Oldfield, Christos Tzelepis, Yannis Panagakis +2
Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entangle…
Unsupervised Discovery of Semantic Concepts in Satellite Imagery with Style-based Wavelet-driven Generative Models
Nikos Kostagiolas, Mihalis A. Nicolaou, Yannis Panagakis
In recent years, considerable advancements have been made in the area of Generative Adversarial Networks (GANs), particularly with the advent of style-based architectures that addr…
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
James Oldfield, Christos Tzelepis, Yannis Panagakis +2
Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich seman…
Tensor Component Analysis for Interpreting the Latent Space of GANs
James Oldfield, Markos Georgopoulos, Yannis Panagakis +2
This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synt…
Classification of Influenza Hemagglutinin Protein Sequences using Convolutional Neural Networks
Charalambos Chrysostomou, Floris Alexandrou, Mihalis A. Nicolaou +1
The Influenza virus can be considered as one of the most severe viruses that can infect multiple species with often fatal consequences to the hosts. The Hemagglutinin (HA) gene of…
Tensor Methods in Computer Vision and Deep Learning
Yannis Panagakis, Jean Kossaifi, Grigorios G. Chrysos +4
Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent…
Enhancing Facial Data Diversity with Style-based Face Aging
Markos Georgopoulos, James Oldfield, Mihalis A. Nicolaou +2
A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as…
Multimodal Joint Emotion and Game Context Recognition in League of Legends Livestreams
Charles Ringer, James Alfred Walker, Mihalis A. Nicolaou
Video game streaming provides the viewer with a rich set of audio-visual data, conveying information both with regards to the game itself, through game footage and audio, as well a…
3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation
Stylianos Moschoglou, Stylianos Ploumpis, Mihalis Nicolaou +2
Over the past few years, Generative Adversarial Networks (GANs) have garnered increased interest among researchers in Computer Vision, with applications including, but not limited…
Adversarial Learning of Disentangled and Generalizable Representations for Visual Attributes
James Oldfield, Yannis Panagakis, Mihalis A. Nicolaou
Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority…
Deep Unsupervised Multi-View Detection of Video Game Stream Highlights
Charles Ringer, Mihalis A. Nicolaou
We consider the problem of automatic highlight-detection in video game streams. Currently, the vast majority of highlight-detection systems for games are triggered by the occurrenc…