244 citations · 824 across the 56 of their papers we have counts for
6 papers · 1 filter
Contrastive Covariance Subspaces for Activation Steering
Alexandros Xenos, Manos Plitsis, Niki Foteinopoulou +2
Activation steering controls large language model behavior by adding a direction to hidden activations during inference. For steering to work well, that direction must be a pure si…
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 offer…
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…
GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection
Aggelos Psiris, Yannis Panagakis, Maria Vakalopoulou +1
Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) comprises a critical task in modern manufacturing settings, where automated product inspection systems need to identify rare…
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…