Tag
This paper introduces SheafDEQ, a subhomogeneous deep-equilibrium architecture with adaptive neural-sheaf propagation that ensures unique equilibrium and convergence in implicit graph neural networks, improving performance on distributed-inference and community detection tasks.
This paper introduces sheaf regularization to stabilize Decentralized SyncMap for unsupervised continual chunking, achieving higher normalized mutual information and better adaptation to input distribution shifts.
This paper defines space as an interventional invariant and develops a cross-modal predictive geometry to unify spatial structure across mathematics, physics, cognition, and urban science.
This paper introduces Sheaf-based Federated Representation Learning (SFRL), a framework that aligns heterogeneous local representations via learnable sheaf restriction maps and a quadratic gluing regularizer, without assuming a shared global latent space. A decentralized algorithm (Sheaf-FRL) with convergence guarantees is proposed and shown to outperform baselines in cooperative classification under data and model heterogeneity.
This paper introduces a categorical framework for constructing verifiable, local truth-preserving foundation models using composable foundries, implemented in the Odyssey system, and scheduled for a tutorial at ICML 2026.
This paper develops a finite sheaf-theoretic framework for detecting scientific theory shift in AI agents by measuring transport and obstruction across representational contexts, and evaluates it on a benchmark designed to separate deformation within a source language from extension of that language.