arXiv cs.NE
· Papers
LayerNorm as Implicit Gain Control in Looped Transformers
arXiv:2607.10681v1 Announce Type: cross Abstract: In pre-LayerNorm looped transformers, LayerNorm inside the recurrent block acts as an implicit gain controller: by coupling the block's local Lipschitz constant inversely to the activation scale, it renders the recurrence Jacobian non-normal -- asymptotically contractiv