[WWW 2026] Official implementation for Riemannian Liquid Spatio-Temporal Graph Network
-
Updated
Feb 11, 2026 - Python
[WWW 2026] Official implementation for Riemannian Liquid Spatio-Temporal Graph Network
Research-grade PyTorch math: differential geometry, spectral graph theory, discrete Ricci flow, simplicial topology, persistent homology, cellular sheaves, SO(3) Lie primitives, information geometry, tensor decompositions, content-addressable provenance. GPU-native, batched-first, audit-clean, cited.
VNAE: A geometric approach to global stability in massive multi-agent systems with asymmetric dissipation, validated at scale.
Research code accompanying a Diploma thesis on topology and geometry in Riemannian autoencoders.
This repository contains the complete supplementary material for the canonical/quadratic example of the VNAE framework.
Abstract power grid dynamics under asymmetric dissipation, illustrating geometric stability in the VNAE framework.
Victoria-Nash Asymmetric Equilibrium (VNAE) framework for massive multi-agent systems. Scalable stability analysis for 10,000+ agents using Riemannian geometry and structural curvature K.
Practical example of the Victoria-Nash Asymmetric Equilibrium (VNAE) applied to multi-agent drone control. Paper: "Riemmanian Manifolds of Asymmetric Equilibria: The Victoria-Nash Geometry".
GAP is a biologically plausible learning algorithm designed for Dynamically Gated Analog Crossbars (DGAC). It bridges the gap between the energy efficiency of local Hebbian learning and the global optimization power of backpropagation by utilizing dynamic Riemannian curvature.
This repository explores the geometric stability of complex biochemical networks using the VNAE framework.
To associate your repository with the riemannian-manifolds topic, visit your repo's landing page and select "manage topics."