EEG-X: Device-Agnostic and Noise-Robust Foundation Model for EEG

arXiv — cs.LG•Thursday, November 13, 2025 at 5:00:00 AM

The introduction of EEG-X marks a significant advancement in EEG analysis, tackling two major challenges: dataset variability and low signal-to-noise ratios. Traditional EEG models often struggle with these issues, leading to less reliable outcomes. EEG-X overcomes these hurdles by employing a device-agnostic framework and a noise-aware masking and reconstruction strategy. This model utilizes a location-based channel embedding to improve generalization across different devices and recording conditions. Furthermore, EEG-X is trained to reconstruct denoised signals, focusing on neural activity rather than noise, which enhances its robustness. Experiments conducted on diverse datasets demonstrate the effectiveness of EEG-X, paving the way for more accurate EEG representation learning and broader applications in neuroscience and clinical settings.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

arXiv — cs.CV2 days ago

Bridging Hidden States in Vision-Language Models

PositiveArtificial Intelligence

Vision-Language Models (VLMs) are emerging models that integrate visual content with natural language. Current methods typically fuse data either early in the encoding process or late through pooled embeddings. This paper introduces a lightweight fusion module utilizing cross-only, bidirectional attention layers to align hidden states from both modalities, enhancing understanding while keeping encoders non-causal. The proposed method aims to improve the performance of VLMs by leveraging the inherent structure of visual and textual data.

Read full article

via arXiv — cs.CV

arXiv — cs.LG2 days ago

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

PositiveArtificial Intelligence

The paper titled 'Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning' introduces a new method called Bias-REstrained Prefix Representation FineTuning (BREP ReFT). This approach aims to enhance the mathematical reasoning capabilities of models by addressing the limitations of existing Representation finetuning (ReFT) methods, which struggle with mathematical tasks. The study demonstrates that BREP ReFT outperforms both standard ReFT and weight-based Parameter-Efficient finetuning (PEFT) methods through extensive experiments.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Transformers know more than they can tell -- Learning the Collatz sequence

NeutralArtificial Intelligence

The study investigates the ability of transformer models to predict long steps in the Collatz sequence, a complex arithmetic function that maps odd integers to their successors. The accuracy of the models varies significantly depending on the base used for encoding, achieving up to 99.7% accuracy for bases 24 and 32, while dropping to 37% and 25% for bases 11 and 3. Despite these variations, all models exhibit a common learning pattern, accurately predicting inputs with similar residuals modulo 2^p.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

STAMP: Spatial-Temporal Adapter with Multi-Head Pooling

PositiveArtificial Intelligence

The article introduces STAMP, a Spatial-Temporal Adapter with Multi-Head Pooling, designed for time series foundation models (TSFMs) specifically applied to electroencephalography (EEG) data. STAMP utilizes univariate embeddings from general TSFMs to model the spatial-temporal characteristics of EEG data effectively. The study demonstrates that STAMP achieves performance comparable to state-of-the-art EEG-specific foundation models (EEGFMs) across eight benchmark datasets used for classification tasks.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

CAT-Net: A Cross-Attention Tone Network for Cross-Subject EEG-EMG Fusion Tone Decoding

PositiveArtificial Intelligence

The study presents CAT-Net, a novel cross-subject multimodal brain-computer interface (BCI) decoding framework that integrates electroencephalography (EEG) and electromyography (EMG) signals to classify four Mandarin tones. This approach addresses the challenges of tonal variations in Mandarin, which can alter meanings despite identical phonemes. The framework demonstrates strong performance, achieving classification accuracies of 87.83% for audible speech and 88.08% for silent speech across 4800 EEG and 4800 EMG trials with 10 participants.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

PositiveArtificial Intelligence

Higher-order Neural Additive Models (HONAMs) have been introduced as an advancement over Neural Additive Models (NAMs), which are known for their predictive performance and interpretability. HONAMs address the limitation of NAMs by effectively capturing feature interactions of arbitrary orders, enhancing predictive accuracy while maintaining interpretability, crucial for high-stakes applications. The source code for HONAM is publicly available on GitHub.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

EMOD: A Unified EEG Emotion Representation Framework Leveraging V-A Guided Contrastive Learning

PositiveArtificial Intelligence

The article discusses EMOD, a new framework for emotion recognition from EEG signals, which addresses the limitations of existing deep learning models. These models often struggle with generalization across different datasets due to varying annotation schemes and data formats. EMOD utilizes Valence-Arousal (V-A) Guided Contrastive Learning to create transferable representations from heterogeneous datasets, projecting emotion labels into a unified V-A space and employing a soft-weighted supervised contrastive loss to enhance performance.

Read full article

via arXiv — cs.LG

arXiv — cs.CV2 days ago

Shrinking the Teacher: An Adaptive Teaching Paradigm for Asymmetric EEG-Vision Alignment

PositiveArtificial Intelligence

The article discusses a new adaptive teaching paradigm aimed at improving the decoding of visual features from EEG signals. It highlights the inherent asymmetry between visual and brain modalities, characterized by a Fidelity Gap and a Semantic Gap. The proposed method allows the visual modality to adjust its knowledge structure to better align with the EEG modality, achieving a top-1 accuracy of 60.2%, which is a 9.8% improvement over previous methods.

Read full article

via arXiv — cs.CV