1
Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs
突破性将生成式视觉基础引入EEG理解，保留脑电信号中的视觉细节，赋能多模态大模型实现通用脑机接口。
arXiv:2605.18172v2 Announce Type: replace Abstract: Leveraging the universal representations of pre-trained LLMs and MLLMs offers a promising path tow…