AI RESEARCH
INCRT: An Incremental Transformer That Determines Its Own Architecture
arXiv CS.LG
•
ArXi:2604.10703v1 Announce Type: new Transformer architectures are designed by trial and Two theorems form the theoretical backbone. The first (homeostatic convergence) establishes that the system always reaches a finite stopping configuration that is simultaneously minimal (no redundant heads) and sufficient (no uncaptured directional energy above the threshold). The second (compressed-sensing analogy) provides a geometric upper bound on the number of heads that this configuration can contain, as a function of the spectral complexity of the task.