xHC: New Paper on Expanding Residual Streams

burny_tech · x · 2026-07-18

The paper xHC: Expanded Hyper-Connections proposes expanding the Transformer's residual stream into N parallel streams, utilizing sparse updates and convolution-style writeback to mitigate information loss and excessive writeback costs after expansion.

The authors report that xHC delivers consistent downstream performance improvements on 18B and 28B MoE models; on the 18B MoE, the average downstream score is 4.0 points higher than mHC. They also note that to reach the same loss, the vanilla baseline requires roughly 1.50× the compute and mHC requires 1.19×, demonstrating that xHC further enhances the feasibility of large-scale residual-stream expansion.

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

Original post →

More from Research

Research channel →