Related papers: Beyond the Birkhoff Polytope: Spectral-Sphere-Cons…

Hyper-Connections (HC) improve residual networks by introducing learnable mixing across multiple residual streams, but unconstrained mixing leads to training instability. Manifold-Constrained Hyper-Connections (mHC) address this by…

Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and diversifying connectivity patterns. While yielding…

Hyper-Connections (HC) generalizes residual connections by introducing dynamic residual matrices that mix information across multiple residual streams, accelerating convergence in deep neural networks. However, unconstrained residual…

The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to its training instability and restricted scalability. The Manifold-Constrained Hyper-Connections (mHC) mitigate these challenges by…

Manifold-Constrained Hyper-Connections (mHC) introduce a stability-motivated variant of multi stream residual mixing by constraining residual stream mixing matrices to the manifold of doubly stochastic matrices via Sinkhorn-Knopp…

Recent advances in deep learning, exemplified by Hyper-Connections (HC), have expanded the residual connection paradigm by introducing wider residual streams and diverse connectivity patterns. While these innovations yield significant…

Doubly-stochastic matrices (DSM) are increasingly utilized in structure-preserving deep architectures -- such as Optimal Transport layers and Sinkhorn-based attention -- to enforce numerical stability and probabilistic interpretability. In…

Hyperspectral sensors capture dense spectra per pixel but suffer from low spatial resolution, causing blurred boundaries and mixed-pixel effects. Co-registered companion sensors such as multispectral, RGB, or panchromatic cameras provide…

Graph-structured data is ubiquitous in scientific domains, where models often face imbalanced learning settings. In imbalanced regression, domain preferences focus on specific target value ranges that represent the most scientifically…

Hyperspectral unmixing allows representing mixed pixels as a set of pure materials weighted by their abundances. Spectral features alone are often insufficient, so it is common to rely on other features of the scene. Matrix models become…

Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer under limited supervision. However, current methods typically rely on single-filter backbones (e.g.,…

Multi-stream transformer architectures have recently been proposed as a promising direction for managing representation collapse and the vanishing gradient problem for residual connections, yet their internal mechanisms remain unexplored.…

While message-passing neural networks (MPNNs) have shown promising results, their real-world impact remains limited. Although various limitations have been identified, their theoretical foundations remain poorly understood, leading to…

In electronic structure theory, restricted single-reference coupled cluster (CC) captures weak correlation but fails catastrophically under strong correlation. Spin-projected unrestricted Hartree-Fock (SUHF), on the other hand, misses weak…

Multi-Agent Reinforcement Learning is widely used for multi-robot coordination, where simple graphs typically model pairwise interactions. However, such representations fail to capture higher-order collaborations, limiting effectiveness in…

In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships. However, current neural network approaches designed for hypergraphs are mostly shallow, thus…

The Sinkhorn algorithm has emerged as a powerful tool for solving optimal transport problems, finding applications in various domains such as machine learning, image processing, and computational biology. Despite its widespread use, the…

Hyperspectral images (HSI) provide rich spectral information that contributed to the successful performance improvement of numerous computer vision tasks. However, it can only be achieved at the expense of images' spatial resolution.…

Efficient data transmission across mobile multi-hop networks that connect edge devices to core servers presents significant challenges, particularly due to the variability in link qualities between wireless and wired segments. This…

Enormous efforts have been recently made to super-resolve hyperspectral (HS) images with the aid of high spatial resolution multispectral (MS) images. Most prior works usually perform the fusion task by means of multifarious pixel-level…