MindAdapter: Few-Shot Parameter-Efficient Residual Calibration of Cross-Subject Brain-to-Visual Decoding Models
MindAdapter: 跨被试脑到视觉解码模型的少样本参数高效残差校准
机构 * Guangdong Institute of Intelligence Science and Technology(广东智能科学与技术研究院) ; Agency for Science, Technology and Research(科技研究局) ; New York University(纽约大学) ; Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) ; Department of Computer and Information Science, University of Macau(澳门大学计算机与信息科学系)
专题命中 BCI数据与评测 :brain-computer interface(abstract)
AI总结 提出MindAdapter框架,通过解耦的线性-残差级联对齐和拓扑锚定双流流形约束,实现跨被试脑到视觉解码的少样本参数高效校准。
Comments Accepted to KDD 2026 (AI4Sciences Track). 15 pages, 7 figures