中国科学院自动化研究所团队创新性地设计了一种多模态集成框架，该框架融合 fMRI 特征提取器与大语言模型，可解决大脑活动的视觉重建问题，增强脑信号解码能力，实现脑信号描述、复杂推理、概念定位和视觉重建等任务。

Modality-agnostic decoders leverage modality-invariant representations in human subjects' brain activity to predict stimuli irrespective of their modality (image, text, mental imagery).

Neuroscientists are using artificial intelligence (AI) machine learning to identify potential predictive biomarkers by finding patterns in the noisy, complex data of brain images. Can AI algorithms ...

Low-resolution images (LR) are input, and feature maps are obtained through 3×3 convolution. After passing through a residual in residual (RIR) module, followed by upsampling and a 3×3 convolution ...

The pathophysiological process of Alzheimer's disease (AD) begins years, even decades, prior to the time a clinical diagnosis can be established. This long asymptomatic or minimally symptomatic phase ...