2 citations · 6 across the 19 of their papers we have counts for
19 papers
Attention-Aware Routing: Coupling Routing and Attention in MoEs
Despoina Kosmopoulou, Anastasios Tsetsilas, Efthymios Georgiou +3
In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual information. We propose Atte…
The Illusion of Balanced Multimodal Sentiment Analysis: Beyond the Limits of Optimization-Based Methods
Ioanna Kaffeza, Efthymios Georgiou, Alexandros Potamianos
Multimodal Sentiment Analysis (MSA) remains constrained by modality imbalance, yet the field continues to rely on optimization-based balancing methods that promise more than they d…
Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS
Georgios Syllas, Efthymios Georgiou, Kosmas Kritsis +1
Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lacking the curated corpora behin…
Segregate, Refine, Integrate: Decomposing Multimodal Fusion for Sentiment Analysis
Alexios Filippakopoulos, Elias Kallioras, Nikolaos Xiros +2
Multimodal fusion must simultaneously refine modality-specific signals and model cross-modal interactions; two competing objectives typically entangled within the same operation. W…
A Benchmark of (MRI-) Foundation Models to Predict IDH Mutational Status in Glioma
Nathan Hollet, Elise Robinson, Efthymios Georgiou +3
Non-invasive prediction of glioma molecular status from routine magnetic resonance imaging (MRI) has shown promising performance, but model generalization remains challenging given…
Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth
Daria Laslo, Efthymios Georgiou, Marius George Linguraru +4
Predicting the spatio-temporal progression of brain tumors is essential for guiding clinical decisions in neuro-oncology. We propose a hybrid mechanistic learning framework that co…
Masked Diffusion Language Models with Frequency-Informed Training
Despoina Kosmopoulou, Efthymios Georgiou, Vaggelis Dorovatas +2
We present a masked diffusion language modeling framework for data-efficient training for the BabyLM 2025 Challenge. Our approach applies diffusion training objectives to language…
A Principled Framework for Multi-View Contrastive Learning
Panagiotis Koromilas, Efthymios Georgiou, Giorgos Bouritsas +3
Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentation…
MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions
Georgios Chatzichristodoulou, Despoina Kosmopoulou, Antonios Kritikos +5
SER is a challenging task due to the subjective nature of human emotions and their uneven representation under naturalistic conditions. We propose MEDUSA, a multimodal framework wi…
DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis
Efthymios Georgiou, Vassilis Katsouros, Yannis Avrithis +1
While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In t…
Y-Drop: A Conductance based Dropout for fully connected layers
Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros Potamianos
In this work, we introduce Y-Drop, a regularization method that biases the dropout algorithm towards dropping more important neurons with higher probability. The backbone of our ap…
PowMix: A Versatile Regularizer for Multimodal Sentiment Analysis
Efthymios Georgiou, Yannis Avrithis, Alexandros Potamianos
Multimodal sentiment analysis (MSA) leverages heterogeneous data sources to interpret the complex nature of human sentiments. Despite significant progress in multimodal architectur…
SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method
Efthymios Georgiou, Alexandros Potamianos
Data augmentation is a prevalent technique for improving performance in various machine learning applications. We propose SeqAug, a modality-agnostic augmentation method that is ta…
Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks
Nikolaos Antoniou, Efthymios Georgiou, Alexandros Potamianos
Designing powerful adversarial attacks is of paramount importance for the evaluation of -bounded adversarial defenses. Projected Gradient Descent (PGD) is one of the most e…
A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking
Eleftherios Kapelonis, Efthymios Georgiou, Alexandros Potamianos
Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations. Recent state-of-the-art DST implementations rely on schemata of d…
Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss
Efthymios Georgiou, Kosmas Kritsis, Georgios Paraskevopoulos +3
Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity. However, they suffer from training stability issu…
MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis
Georgios Paraskevopoulos, Efthymios Georgiou, Alexandros Potamianos
Current deep learning approaches for multimodal fusion rely on bottom-up fusion of high and mid-level latent modality representations (late/mid fusion) or low level sensory inputs…
AudioVisual Speech Synthesis: A brief literature review
Efthymios Georgiou, Athanasios Katsamanis
This brief literature review studies the problem of audiovisual speech synthesis, which is the problem of generating an animated talking head given a text as input. Due to the high…
End-to-end Generative Zero-shot Learning via Few-shot Learning
Georgios Chochlakis, Efthymios Georgiou, Alexandros Potamianos
Contemporary state-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. Thereafter, classifiers are…