📄 中文摘要
MindPilot 是首个闭环框架，利用 EEG 信号作为优化反馈，指导自然图像生成。与以往仅限于侵入性设置或低级闪烁刺激的研究不同，MindPilot 采用非侵入性 EEG 结合自然图像，旨在通过控制刺激来引导大脑活动。设计能够一致引发期望神经反应的图像面临挑战，主观状态缺乏明确的量化指标，EEG 反馈则噪声大且不可微分。该框架为理解视觉领域中的大脑调制提供了新的视角和方法。通过优化过程，能够更有效地探索大脑与视觉刺激之间的关系。
MindPilot：基于 EEG 引导的扩散闭环视觉刺激优化用于大脑调制
📄 English Summary
MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion
MindPilot is the first closed-loop framework that utilizes EEG signals as optimization feedback to guide the generation of naturalistic images. Unlike previous studies limited to invasive settings or low-level flicker stimuli, MindPilot employs non-invasive EEG in conjunction with natural images, aiming to steer brain activity through controlled stimuli. Designing images that consistently elicit desired neural responses poses significant challenges, as subjective states lack clear quantitative measures and EEG feedback is both noisy and non-differentiable. This framework offers a novel perspective and methodology for understanding brain modulation in the visual domain. Through the optimization process, it enables a more effective exploration of the relationship between the brain and visual stimuli.