Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks

arXiv:2602.15997v2 Announce Type: replace Abstract: Capability emergence during neural network training remains mechanistically opaque. We track five geometric measures across five model scales (405K-85M parameters), 120+ emergence events in eight algorithmic tasks, and three ...

🔗 Read more: https://arxiv.org/abs/2602.15997

#News #Software #WorldNews #AI #Neuro #Policy #Academic