Konstantinos Kontras

B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet

Jaedong Hwang, Kathleen Zhang, Wei Dai, Konstantinos Kontras et autres

EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical and brain-computer interface tasks. Existing models typically discretize the continuous multi-channel EEG waveform into patches or codebook tokens and train a transformer with masked …

B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet

Jaedong Hwang, K Zhang, Wei Dai, Konstantinos Kontras et autres

EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical and brain-computer interface tasks. Existing models typically discretize the continuous multi-channel EEG waveform into patches or codebook tokens and train a transformer with masked …

NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

Konstantinos Kontras, Trui Osselaer, Stylianos G. Mouslech, Angeliki-Ιlektra Karaiskou et autres

Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG), but it is less clear how effective they are in this particular field. Published evaluations differ in datasets, in the EEG-specific …

NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

Konstantinos Kontras, Trui Osselaer, Stylianos G. Mouslech, Angeliki-Ιlektra Karaiskou et autres

Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG), but it is less clear how effective they are in this particular field. Published evaluations differ in datasets, in the EEG-specific …

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

Konstantinos Kontras, Teodora Gagaleska, Thomas Strypsteen, Christos Chatzichristos et autres

A central objective in multimodal learning is to capture synergy: task-relevant information that arises only from the joint use of multiple modalities, and is not available from any single modality alone. While most approaches operate at the architectural level through larger or …

SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

Konstantinos Kontras, Teodora Gagaleska, Thomas Strypsteen, Christos Chatzichristos et autres

A central objective in multimodal learning is to capture synergy: task-relevant information that arises only from the joint use of multiple modalities, and is not available from any single modality alone. While most approaches operate at the architectural level through larger or …

ru, be, cn (code pays fourni par la source)

Self-Balancing Multimodal Models via Multi-Loss Gradient Modulation

Konstantinos Kontras, Christos Chatzichristos, Matthew Blaschko, Maarten De Vos

be (code pays fourni par la source)

Bird-MML: A Multimodal Dataset for Audio-Visual Complementarity

Stefanos Koutoupis, Michaela Areti Zervou, Konstantinos Kontras, Maarten De Vos et autres

Bird-MML is a synthetic multimodal dataset designed to study cross-modal representation learning and multimodal complementarity across vision, audio, and text. Despite substantial progress in multimodal learning, there remains a lack of standardized datasets that support the evaluation of both pairwise and higher-order …

Balancing Multimodal Training Through Game-Theoretic Regularization

Konstantinos Kontras, Thomas Strypsteen, Christos Chatzichristos, Paul Liang et autres

be, ru (code pays fourni par la source)

Balancing Multimodal Training Through Game-Theoretic Regularization

Konstantinos Kontras, Thomas Strypsteen, Christos Chatzichristos, Paul Pu Liang et autres

Multimodal learning holds promise for richer information extraction by capturing dependencies across data sources. Yet, current training methods often underperform due to modality competition, a phenomenon where modalities contend for training resources leaving some underoptimized. This raises a pivotal question: how can …

CoRe-Sleep: A Multimodal Fusion Framework for Time Series Robust to Imperfect Modalities

Konstantinos Kontras, Christos Chatzichristos, Huy Phan, Johan A. K. Suykens et autres

Sleep abnormalities can have severe health consequences. Automated sleep staging, i.e. labelling the sequence of sleep stages from the patient's physiological recordings, could simplify the diagnostic process. Previous work on automated sleep staging has achieved great results, mainly relying on the EEG …

be, us, gb (code pays fourni par la source)

CoRe-Sleep: A Multimodal Fusion Framework for Time Series Robust to Imperfect Modalities

Konstantinos Kontras, Christos Chatzichristos, Huy P. Phan, Johan A. K. Suykens et autres

Sleep abnormalities can have severe health consequences. Automated sleep staging, i.e. labelling the sequence of sleep stages from the patient's physiological recordings, could simplify the diagnostic process. Previous work on automated sleep staging has achieved great results, mainly relying on the EEG …