collaborators

10 papers

cs.LG2026

Loss-Shift Transfer via Bayes Quotients

Vasileios Sevetlidis

Transfer learning is usually studied as a consequence of distribution shift. This paper identifies an orthogonal failure mode in which the data distribution is fixed and the loss c…

cs.LG2026

Bayes-Sufficient Representations in Supervised Learning

Vasileios Sevetlidis

Representation learning is often described as preserving the information in an input that is relevant for prediction. This work asks what relevance means for a fixed supervised dec…

cs.LG2026

A Fiber Criterion for Representation Identifiability in Supervised Learning

Vasileios Sevetlidis

Supervised learning evaluates predictors through their input-output behavior. When a predictor is implemented as a composition , supervised evidence constrains the comp…

cs.CV2026

Towards complete digital twins in cultural heritage with ART3mis 3D artifacts annotator

Dimitrios Karamatskos, Vasileios Arampatzakis, Vasileios Sevetlidis +5

Archaeologists, as well as specialists and practitioners in cultural heritage, require applications with additional functions, such as the annotation and attachment of metadata to…

cs.CV2026

ART3mis: Ray-Based Textual Annotation on 3D Cultural Objects

Vasileios Arampatzakis, Vasileios Sevetlidis, Fotis Arnaoutoglou +7

Beyond simplistic 3D visualisations, archaeologists, as well as cultural heritage experts and practitioners, need applications with advanced functionalities. Such as the annotation…

cs.LG2026

Gauge-invariant representation holonomy

Vasileios Sevetlidis, George Pavlidis

Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness. Existing similarity measures such as…