AI RESEARCH
MANAR: Memory-augmented Attention with Navigational Abstract Conceptual Representation
arXiv CS.AI
•
ArXi:2603.18676v1 Announce Type: new MANAR (Memory-augmented Attention with Navigational Abstract Conceptual Representation), contextualization layer generalizes standard multi-head attention (MHA) by instantiating the principles of Global Workspace Theory (GWT). While MHA enables unconstrained all-to-all communication, it lacks the functional bottleneck and global integration mechanisms hypothesized in cognitive models of consciousness. MANAR addresses this by implementing a central workspace through a trainable memory of abstract concepts and an Abstract Conceptual Representation.