Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

xHC: Expanded Hyper-Connections Enable Residual Stream Scaling Beyond N=4

AI By Crimson AI Hugging Face Papers 20 July 2026 · 00:00 7 views
Share: X Telegram

Hugging Face researchers propose xHC, a method that expands the residual stream of Transformers to N=16 parallel streams, overcoming bottlenecks that limited prior Hyper-Connection methods to N=4. xHC delivers consistent downstream improvements in 18B and 28B MoE models with modest training cost.

xHC: Expanded Hyper-Connections Enable Residual Stream Scaling Beyond N=4

Key points

Researchers from Hugging Face have introduced xHC (Expanded Hyper-Connections), a novel method that pushes the residual stream expansion of Transformers beyond the previous limit of N=4 parallel streams. The work addresses fundamental bottlenecks that prevented earlier Hyper-Connection (HC) methods from scaling effectively.

The standard Hyper-Connections expand the residual stream into N parallel streams, offering a form of memory scaling. However, prior Manifold-Constrained HC (mHC) showed diminishing returns and rapidly increasing training costs beyond N=4. The authors identify two key bottlenecks: insufficient write-back information for many streams, and cubic scaling of residual-mixing generation cost with N.

xHC introduces two innovations: temporal feature augmentation for richer write-back, and a sparse residual-stream architecture that updates only k=4 of N=16 streams while retaining dense access to the full residual state. This design enables meaningful expansion beyond N=4 for the first time in the HC family.

Experiments on 18B and 28B MoE models show strong gains. On the 18B model, xHC lowers the final training loss from 1.776 to 1.758 and raises the average downstream score from 44.8 to 48.8 over DeepSeek mHC, with broad improvements across reasoning, knowledge, and code tasks, while adding only 4.1% training FLOPs over the vanilla baseline. At 28B, xHC outperforms mHC by 3.1 average points.

Scaling-law experiments reveal that vanilla and mHC require 1.50× and 1.19× the compute of xHC, respectively, to reach the same loss. To manage memory traffic from the expanded residual state, the authors also introduce xHC-Flash, which reduces per-sublayer memory traffic from 73.5C to 40C, comparable to the 34C of mHC at N=4, while preserving full xHC gains.

ModelMethodFinal LossAvg Downstream ScoreTraining FLOPs Overhead
18B MoEVanillaBaseline
18B MoEmHC (DeepSeek)1.77644.8
18B MoExHC1.75848.8+4.1%
28B MoEmHC
28B MoExHC+3.1 vs mHC
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1