collaborators

18 papers

cs.CV2026

Sparsity-Inducing Divergence Losses for Biometric Verification

Dimitrios Koutsianos, Ladislav Mošner, Yannis Panagakis +1

Performance in face and speaker verification is largely driven by margin-penalty softmax losses such as CosFace and ArcFace. Recently introduced -divergence loss functions offe…

cs.LG2026

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search

Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros +1

Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gende…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

Konstantinos Barmpas, Na Lee, Dimitrios Chalatsis +7

Biosignals such as electroencephalography (EEG), electrocardiography (ECG), and electromyography (EMG) encode physiological activity across multiple temporal and spectral scales, y…

cs.LG2026

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…