xHC: Scaling Residual Streams by 16x

teortaxesTex · x · 2026-07-17

This content focuses on a new architecture called xHC, aiming to further expand residual streams to boost model capacity and expressiveness.

It notes that early Hyper-Connections and mHC already proved that "residual streams don't have to be single-path," but original designs remained limited when scaling up. The proposed xHC uses temporal feature augmentation and a sparse residual stream architecture to simultaneously solve shared write-back components and rapidly growing generation costs at scale. It claims to effectively widen the residual stream significantly (mentioned as roughly 16x).

Related event: xHC Architecture: Expanding Transformer Residual Streams into Parallel Flows(2 posts)→

Original post →

More from Research

Research channel →