Skip to content
#

stable-training

Star

Here are 2 public repositories matching this topic...

fardinsabid / wHC

Star 1

Wormhole Hyperconnections — Drop-in replacement for residual connections (x + F(x) → WHC). 50x faster at scale. 93 params. Proven stable.

machine-learning deep-learning optimization pytorch neural-networks gradient-descent research-paper manifold-learning whc gradient-flow pytorch-library spectral-norm drop-in-replacement residual-connections ml-research stable-training fast-training physics-inspired-ml wormhole-hyperconnections hyperconnection
  • Updated Jul 16, 2026
  • Python

Improve this page

Add a description, image, and links to the stable-training topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the stable-training topic, visit your repo's landing page and select "manage topics."

Learn more