KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices 事件

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices arXiv:2601.21579v2 Announce Type: replace Abstract: The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to training instability and restricted scalability. The Manifold-Constrained Hyper-Connections (mHC) mitigate these challenges by projecting the residual connection space onto a Birkhoff polytope, however, it faces two issues: 1) its iterative Sinkhorn-Knopp (S