Research Highlights

The paper “Prescriptive SVD-Inspired Attention via Spectral Energy Retention” has been published in Transactions on

The article “Towards Heritage World Models” extends the discussion around ARGUS, PANOPTES, semantic digital twins

“Representation-Diverse Self-Supervision for Cross-Domain Bioacoustic Learning in Low-Resource Settings” was presented at ICASSP 2026. The

The paper “Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability” was published

“Two-Stage Angular Alignment for Positive-Unlabeled Learning” proposes a geometric weak-supervision method for settings where only

“Interpretable Vision Transformers in Image Classification via SVDA” extends the group’s SVD-inspired attention work to

The paper “Angular Regularization for Positive-Unlabeled Learning on the Hypersphere” received TMLR certification and was

“Krikri: Advancing Open Large Language Models for Greek” was published in Findings of EMNLP 2025

The article “Towards Evolving Actor-Network Ontologies: Enabling Reflexive Digital Twins for Cultural Heritage” advances the

The paper “AHMP: Agile Humanoid Motion Planning with Contact Sequence Discovery” was presented at IEEE-RAS