A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks 事件

A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks arXiv:2510.24342v2 Announce Type: replace Abstract: Prior brain-AI alignment studies are typically constrained by specific inputs and tasks, limiting their ability to capture organizational properties across models with different modalities. In this work, we focus on Transformer-based models and introduce a brain-model topological alignment space. Rather than inferring alignment from ne