The paper introduces BraVista, a visual-language framework that transforms multichannel EEG signals into structured images and uses instruction‑conditioned vision‑language models for unified multi‑task EEG decoding. By continuing post‑training of a general‑domain VLM, BraVista adapts to neural signals without large‑scale EEG‑specific pretraining, achieving strong performance across sleep staging, emotion recognition, cognitive workload classification, and abnormal EEG detection. Analyses show that the EEG‑to‑image representation is crucial and that the model’s performance degrades gradually with added noise, indicating reliance on genuine EEG information.
By Parastoo Azizeddin, Omid Sharafi, Maryam M. Shanechi
arXiv:2506. 17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings.
By Yuan Zhong, Ruinan Jin, Qi Dou, Xiaoxiao Li
OneEEG is a unified signal‑visual multimodal language model designed for multi‑task EEG understanding. It jointly learns from numerical EEG data and visual EEG renderings, employing a task‑aware Mixture of Projectors to align diverse EEG features with a large language model’s embedding space. The authors introduce the OneEEG‑Instruct dataset for instruction tuning and the OneEEG‑Bench benchmark to evaluate performance, demonstrating that existing multimodal LLMs struggle with EEG inputs while OneEEG outperforms them across various tasks.
By Jiacheng Zhang, Xueyi Zhang, Xin Lu, Siqi Cai, Haizhou Li
arXiv:2609.17443v1 Announce Type: new
Abstract: Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expe...
By Yihui Peng, Guorui Lu, Qinyu Chen
EEG-to-Report is a browser-based annotation and feature‑text framework that links routine EEG review with the creation of AI‑ready datasets. It ingests multi‑format EEG data, standardizes channels, and provides an interactive viewer with a multimodal annotation layer that combines typed text and transcribed voice notes. For each annotated segment, a feature extraction engine computes standardized spectral, temporal, entropy, Hjorth, connectivity, and spike‑related descriptors, stored alongside clinical descriptions in a portable JSON schema, producing aligned feature‑text pairs for training multimodal EEG‑language models. The framework also includes an auto‑report module that uses an ensemble of convolutional networks and a large language model to draft clinical narratives for neurologist review, thereby streamlining annotation workflows and enabling editable draft reports.
By Xuan-The Tran, Le Trung Kien Nguyen
arXiv:2607. 21402v1 Announce Type: new Abstract: Self-supervised foundation models have recently shown strong potential for electroencephalogram (EEG)-based analysis.
By Tao Zhou, Jing Han, Lingyu Shu, Zixing Zhang
arXiv:2609.38362v1 Announce Type: new
Abstract: Generative vision-language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining dis...
By Hung-Jen Chen, Yu-Heng Ho, Ting-Yao Huang, Po-Hsiang Hsu, Li-Yu Chen, Chun-Yi Lee, Min Sun
arXiv:2601. 17883v3 Announce Type: replace Abstract: Electroencephalography (EEG) foundation models (FMs) have recently emerged as a promising paradigm for brain-computer interfaces, aiming to learn transferable neural representations from large-scale heterogeneous recordings.
By Dingkun Liu, Yuheng Chen, Zhu Chen, Zhenyao Cui, Yaozhi Wen, Jiayu An, Jingwei Luo, Dongrui Wu
arXiv:2607. 21384v1 Announce Type: new Abstract: Electroencephalography (EEG) models used for epilepsy are often limited to specific datasets and tasks.
By Targol Bakhtiarvand, Jugal Kalita, Adham Atyabi
arXiv:2606. 20077v1 Announce Type: cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals.
By Wish Suharitdamrong, Tony Alex, Muhammad Awais, Sara Atito
EEG-AS is an instance-level algorithm selection framework designed for EEG foundation models. It characterizes each EEG instance using latent embeddings, handcrafted neurophysiological features, and an anchor foundation model, then learns to reconstruct the behaviors of other foundation models from privileged prediction tokens. During inference, EEG-AS estimates these behaviors without running the full model portfolio, enabling efficient selection among seven EEG foundation models and significantly reducing the performance gap between the single best solver and the oracle upper bound across seven public EEG benchmarks.
By Yunzhen Zhang, Ruoxi Piao, Hasan Onur Keles, Mustafa Misir
arXiv:2605. 30170v2 Announce Type: replace-cross Abstract: While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting.
By Xingzhou Pang, Yifan Hou, Junling Wang, Mrinmaya Sachan