arXiv 주간 스캔

AI가 생성한 요약

• 서로 다른 범주의 분자들이 같은 비트열로 압축되는 충돌을 줄이도록 화학 모델의 표현을 조정한다.
• ChemBERTa와 양자 회로 시뮬레이션으로 분자의 혈뇌장벽 투과 여부를 예측했다.
• 10큐비트 조건에서 같은 입력을 받는 로지스틱 회귀보다 높은 정확도를 보고했으며, 특정 비교 조건의 결과다.

의의

이산화 과정의 정보 손실이 후속 분류에 미치는 영향을 검토한다.

연구실 연구와의 관련성

뇌 표현을 압축할 때의 정보 손실을 점검하는 참고 방법이다. fMRI나 EEG에 적용한 결과는 이 논문에서 검증되지 않았다.

요약 · 영문

• EEG-PRIME is a novel two-stage foundation model for EEG decoding designed to overcome cross-dataset and cross-subject generalization issues.
• It employs masked pretraining with spectral augmentation followed by prototype-aligned instruction tuning, incorporating task-semantic, dataset-specific, and subject-invariant conditioning for robust decoding.
• EEG-PRIME demonstrates superior performance on diverse EEG tasks and exhibits strong zero-shot transfer capabilities on unseen datasets, outperforming existing baselines and foundation models.

의의

This work represents a significant advancement in EEG decoding by developing a foundation model capable of robust and generalizable performance across diverse datasets and subjects without extensive calibration, paving the way for more practical brain-computer interfaces.

연구실 연구와의 관련성

The development of EEG-PRIME aligns with the SNU Connectome Lab's Neuro-X initiative, as it focuses on creating generalizable AI models for neural signal decoding, a critical component for advancing neurotechnology.

요약 · 영문

• EEG-PRISM is a novel method that translates time-channel attribution scores from EEG foundation models into more physiologically relevant domains, specifically the frequency and source domains, without altering the original model.
• The method utilizes linear transformations, including an invertible DFT for frequency mapping and an approximately invertible EEG generative model for source localization, to provide clinically intuitive interpretations.
• Evaluations in both simulated and real EEG data (epilepsy and autism) demonstrated EEG-PRISM's effectiveness in recovering ground-truth spectral activity and localizing seizure onset regions and predictive biomarkers with reasonable accuracy.

의의

This work introduces a crucial tool for making advanced EEG foundation models interpretable in a clinically meaningful way, thereby enabling better understanding of neural mechanisms and identification of disease biomarkers.

연구실 연구와의 관련성

EEG-PRISM's focus on interpretable AI for EEG foundation models directly aligns with SNU Connectome Lab's Neuro-X initiative, which aims to develop advanced neurotechnology with a strong emphasis on understanding and explaining neural data.

요약 · 영문

• The paper proposes Brain Latent Predictive Model (BLPM), an EEG-language foundation model that redefines EEG decoding as a continuous semantic embedding prediction problem.
• BLPM introduces a Continuous EEG Latent Predictive (CELP) encoder for learning transferable representations and a Multi-Query Semantic Decomposition (MQSD) module for aligning EEG with textual semantics in a shared latent space.
• The model aims to overcome limitations of masked autoencoding and autoregressive modeling in current EEG foundation models by prioritizing task-relevant semantics and addressing the mismatch between continuous neural dynamics and discrete token spaces.

의의

This work establishes a novel paradigm for EEG-language foundation models, demonstrating improved generalization and alignment of continuous EEG signals with natural language semantics.

연구실 연구와의 관련성

This research is highly relevant to the 'Large Brain Models' and 'Neuro-X' initiatives at the SNU Connectome Lab, as it advances the development of foundation models for integrating brain activity with artificial intelligence and language processing.

요약

• 중복된 EEG 토큰을 특징 크기를 보존하며 합쳐, Transformer 층이 처리할 시퀀스를 줄인다.
• 여러 EEG 모델과 데이터셋에서 압축 방법을 비교했으며, 압축하지 않은 모델 대비 성능은 조건에 따라 달랐다.
• LaBraM을 로컬 장치에서 실행한 사례에서 추론 시간 감소를 보고했다.

의의

토큰 압축과 분류 성능, 실행 시간의 관계를 평가한다. 장치 성능 측정이 임상 유용성을 입증하는 것은 아니다.

연구실 연구와의 관련성

Neuro-X의 EEG 모델에 시험해 볼 압축 방법이다. 어떤 예측 정보가 유지되거나 사라지는지 함께 평가할 수 있다.

요약 · 영문

• This paper introduces a novel security risk in EEG foundation models: adversarial transfer attacks from public encoders to private downstream models.
• They propose SW-ProxyCE, a query-free attack framework that leverages shrinkage-whitened class prototypes from a small labeled reference set to generate transferable adversarial examples.
• SW-ProxyCE effectively attacks inaccessible downstream models across various EEG tasks and foundation encoders, outperforming task-agnostic attacks and demonstrating that foundation model transferability does not imply adversarial robustness.

의의

This research highlights a critical security vulnerability in the deployment of EEG foundation models, urging the development of robust defenses to protect private downstream applications.

연구실 연구와의 관련성

This work is highly relevant to Neuro-X, as it addresses critical security and robustness challenges pertinent to the deployment and trustworthiness of large-scale neural data models.

요약 · 영문

• STEAM is a novel spatio-temporal alignment Mixture-of-Experts (MoE) model designed for EEG decoding, addressing challenges in generalizability and adaptation costs of conventional BCI algorithms.
• It employs a dual-branch spatio-temporal encoder with a Shared Soft Mixture-of-Experts (SSMoE) module to align and exchange information between spatial and temporal representations.
• The model utilizes a hierarchical pre-training strategy that allows for general initialization and subsequent specialization to specific EEG paradigms, achieving superior performance across diverse datasets and evaluation settings.

의의

This work introduces a foundational model for EEG decoding that significantly advances the generalizability and adaptation efficiency of BCI systems, crucial for widespread adoption in clinical and rehabilitative applications.

연구실 연구와의 관련성

STEAM aligns with the Connectome Lab's focus on Large Brain Models and Neuro-X by developing a sophisticated deep learning architecture for robust and generalizable neural signal decoding, applicable to understanding and leveraging complex brain activity.

요약 · 영문

• EEG foundation models exhibit a pervasive low-frequency bias in their learned representations, irrespective of data scale, model capacity, or pretraining objective.
• This bias stems from the interplay between EEG's $1/f^α$ spectral characteristics and neural networks' natural inclination to prioritize low-frequency components, exacerbated by $\ell_2$ reconstruction losses in masked autoencoders.
• FAME (Frequency-balanced Masked Autoencoding) is proposed, which balances spectral supervision by reconstructing time-frequency activity in predefined EEG bands with independent standardization and equal loss weighting, leading to improved, spectrally balanced representations and state-of-the-art performance on 24 out of 41 downstream tasks.

의의

This research identifies a critical and persistent spectral bias in EEG foundation models, offering a novel frequency-balanced solution that significantly improves representation learning and downstream task performance, pushing the boundaries of transferable EEG AI.

연구실 연구와의 관련성

This work directly impacts the development of Large Brain Models and Neuro-X initiatives at SNU Connectome Lab by providing crucial insights and a solution for training more effective and balanced EEG foundation models, which are fundamental components for understanding brain activity across diverse tasks and populations.

요약 · 영문

• EEG-JEPA introduces a structured latent-prediction framework for EEG foundation modeling, moving beyond simple masked waveform reconstruction to infer latent states.
• The framework employs a masked context encoder and predictor to infer contextual latent states from a target encoder observing complete input, utilizing Neurotopology-Aware Multi-scale Electrode-Temporal Masking (N-MET) for structured electrode-time prediction.
• EEG-JEPA demonstrates significant improvements in frozen multitask transfer (from 40.49% to 50.42%) and full fine-tuning (from 68.98% to 70.65%) compared to masked waveform reconstruction, setting new benchmarks on EEG-FM-Bench.

의의

This work establishes a more effective pretraining strategy for EEG foundation models, enabling them to learn more transferable and neurally relevant representations by predicting structured latent states rather than noisy raw signals.

연구실 연구와의 관련성

This research is highly relevant to the 'Large Brain Models' focus of the SNU Connectome Lab, as it develops advanced foundation models for EEG, a key modality for understanding brain function, and optimizes their pretraining for better generalizability and transferability across various tasks.

요약

• 전뇌 fMRI를 시공간 패치의 시퀀스로 바꾸고, 뇌 밖 배경 토큰을 제거해 학습한다.
• UK Biobank·ABCD·HCP 데이터로 자기회귀 사전학습하고, HCP 성별 분류에 미세조정했다.
• 배경 제거의 계산량 감소와 분류 성능을 평가했으며, 기존 모델과의 비교는 데이터 분할이 다르다.

의의

세밀한 공간 정보를 유지하는 전뇌 학습의 계산 부담을 줄이는 방법을 제시한다.

연구실 연구와의 관련성

Neuro-X의 전뇌 표현 학습을 계산 효율의 문제로 확장한다.

요약

• ABCD 아동 자료에서 유전·뇌·행동·생활환경 사이의 관계를 분석했다.
• 33개 형질의 다유전자 점수와 여러 MRI, 인지·정신건강·환경 지표의 공변 패턴을 살폈다.
• 인지 관련 유전 점수와 뇌 측정치의 공변 패턴을 찾았으며, 별도의 PGS–비영상 분석에서는 지역 소득·빈곤·부모 수용성도 공변 성분에 포함됐다.

의의

유전적 차이를 뇌와 생활 맥락에 함께 놓고 개인차를 탐구하는 근거를 제공한다.

연구실 연구와의 관련성

유전–뇌–행동–환경의 다층 연결을 연구하는 구체적 사례다.

요약

• EEG 채널 순서가 달라도 일관된 표현을 배우도록 시공간 어텐션과 채널 순열 등변성을 결합했다.
• 사전학습 후 정서 인식(32채널)과 운동심상 분류(64채널)에 미세조정했다.
• 합성 채널 순열에서 안정성을 확인했으며, 과제에 따라 비교 모델 대비 성능이 달랐다.

의의

기록마다 달라지는 채널 순서를 모델 설계와 전이 평가의 문제로 다룬다.

연구실 연구와의 관련성

연구실의 EEG 표현 학습을 기록 조건의 차이에 대응하는 설계로 구체화한다.

요약 · 영문

• Critiques the traditional linear regression assumption between LLM activations and fMRI responses.
• Shows that nonlinear multimodal mappings recover brain-language correspondence that linear encodings underestimate.
• Connects predictive-processing views of cortex with autoregressive Transformer internal states.

의의

Re-evaluates the mathematical foundation of how artificial neural representations correspond to biological neural activity.

연구실 연구와의 관련성

Connectome Lab preprint; theoretical grounding for the Neuro-X Large Brain Model initiative.