182 citations · 221 across the 37 of their papers we have counts for
23 papers · 1 filter
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…
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…
Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance
Ioannis Kalogeropoulos, Giorgos Bouritsas, Yannis Panagakis
As machine learning models are increasingly deployed in high-stakes settings, e.g. as decision support systems in various societal sectors or in critical infrastructure, designers…
EEG-D3: A Solution to the Hidden Overfitting Problem of Deep Learning Models
Siegfried Ludwig, Stylianos Bakas, Konstantinos Barmpas +5
Deep learning for decoding EEG signals has gained traction, with many claims to state-of-the-art accuracy. However, despite the convincing benchmark performance, successful transla…
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…