Introduces U$^2$Mamba, a U-structured network for salient object detection with improved local feature extraction and contextual information.

Sublinearly structured DNNs achieve feature-learning and prediction consistency comparable to classical models

The paper introduces UEmbed, a decoder-only multimodal embedding model that produces both sparse lexical and dense representations in one forward pass.

PrunePath introduces a budget-adaptive structured sparsification framework that efficiently prunes Feed-forward networks in large language models, achieving hardware-friendly sparsity and measurable s…

This paper introduces structured cut sets, a novel preprocessing technique for Maximum k-Cut, and extends existing techniques from Maximum Cut. The rules are optimality-preserving and yield significan…

This paper proposes Hierarchical Block-Local Learning (HBLL), a framework for training deep neural networks without full end-to-end backpropagation, achieving $\mathcal{O}(\log N)$ parallel time compl…

An approach is described to support rigid α canonical variables in an e-graph.

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

This paper presents an optimized algorithm for computing cut sets of a path set in graph theory and introduces a vectorized computational framework for property calculations.

The paper introduces Graph Cascades, a mesoscopic rewiring technique that enhances Graph Neural Networks by promoting node pairs with strong multi-hop connections to direct edges, improving performanc…

This paper introduces new activation functions for neural networks to achieve arbitrary-accuracy Sobolev approximation.

The paper proposes a semi-relaxed Gromov-Wasserstein objective to estimate the latent connectivity structure of large-scale networks, achieving statistically consistent and efficient recovery of the u…

This paper proposes a scalable topological learning framework for higher-order graph representation by introducing simplified and factored cellular Weisfeiler Leman tests and a novel random walk metho…

The paper introduces Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning that achieves the standard inductive rate and matches the transductive minima…

This paper studies a random compositional model for the growth of affine regions in deep piecewise-linear networks and proves the existence of a submultiplicative pressure for the number of affine pie…

The authors propose a method called highway error propagation (HEP) to scale predictive coding networks (PCNs) to deeper architectures.

This paper studies the expressive power of tree-structured compositions of EML functions for function approximation.