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。

Researchers have joined forces to give a boost to spatial memory by creating a unique experimental setup that combines non-invasive deep-brain stimulation, virtual reality training, and fMRI imaging.

A 10-minute brain scan can predict the effectiveness of a risky spinal surgery to alleviate intractable pain. The result gives doctors a much-needed biomarker to discuss with patients considering ...

Researchers discover that language and Theory of Mind originate in separate brain regions in children, challenging theories of overlapping cognitive development.

Meta can now simulate how your brain will respond to a video before a single real viewer has watched it. TRIBEv2, released by ...