# What DeepSeek changed with mHC

> Read the research on residual connections and why unrestricted mixing can make model training unstable.

Source: https://fullbytedeveloper.com/blog/deepseek-manifold-constrained-hyper-connections
Originally posted: 2026-01-03
Published here: 2026-11-06

DeepSeek's mHC paper studies how information moves through a neural network's residual connections. It was submitted on December 31, 2025, with a revision on January 5, 2026. [1]

## Identify the problem

The paper builds on Hyper-Connections, which widen the residual stream and introduce more ways to connect it. The authors report that this flexibility can disrupt the identity-mapping behavior of ordinary residual connections, causing unstable training and additional memory-access costs. [1]

## Understand the proposed constraint

Manifold-Constrained Hyper-Connections restrict the space in which those connections can change. The authors combine that constraint with implementation work intended to control the overhead. Their experiments report more stable scaling and performance improvements. [1]

## Keep the result in scope

This is architecture research. It does not provide a switch that makes an existing chatbot preserve every fact in a conversation. Read the experiment settings and comparisons in the paper before applying its findings to a particular model. [1]

## Sources

1. [mHC research paper](https://arxiv.org/abs/2512.24880)

## Original posts

- [Instagram post](https://www.instagram.com/fullbytedeveloper/p/DTDyHjtjpPj/)