graph neural networks

FoldFlow: A Systematic Study of Bio-Inspired Inductive Biases for Neural Architecture Design (v1.1.0)

Adds the WikiText-2 single-component ablations re-run under the corrected causal energy gate, for round 2 of the Scientific Reports revision. Same harness, seeds (42-46), 17-epoch schedule and hardware as the post-fix headline runs in results/tier_b_full/, so every configuration is directly comparable to the post-fix f...

The Fractal Graph Rewriting Framework: A Scale-Dependent Approach to LLM Optimization

FGRF v2.0: Version 2 represents an evolution from the original proof-of-concept. It reframes FGRF from a direct optimizer into a structural integrity probe for neural networks. FGRF v1.0: Initial public release of the FGRF framework for optimizing LLMs without retraining.License: Code (.py files) is MIT licensed. Paper...

The Fractal Graph Rewriting Framework: A Scale-Dependent Approach to LLM Optimization

FGRF v2.0: Version 2 represents an evolution from the original proof-of-concept. It reframes FGRF from a direct optimizer into a structural integrity probe for neural networks. FGRF v1.0: Initial public release of the FGRF framework for optimizing LLMs without retraining.License: Code (.py files) is MIT licensed. Paper...

FoldFlow: A Systematic Study of Bio-Inspired Inductive Biases for Neural Architecture Design (v1.1.0)

Adds the WikiText-2 single-component ablations re-run under the corrected causal energy gate, for round 2 of the Scientific Reports revision. Same harness, seeds (42-46), 17-epoch schedule and hardware as the post-fix headline runs in results/tier_b_full/, so every configuration is directly comparable to the post-fix f...

Finding and characterising physical states of Euclidean Abelianized loop quantum gravity using neural quantum states

Abstract We study physical (near-kernel of constraints) states of 4-d Euclidean loop quantum gravity in Smolin's weak coupling limit on the complete graph $K_5$ using variational Monte Carlo with neural network quantum states. We investigate the Hamilton constraint $\hat{H}$ in the ordering proposed by Thiemann, as wel...

AI in energy and water conservation

AI-Enabled National Water Conservation and Security System for Qatar A Research and Policy Framework for an Intelligent National Water Digital Twin, Predictive AI and ILM-Based Water Intelligence Platform Prepared as a concept paper for Qatar Government consideration Abstract Qatar’s water security challenge is fundame...

Verified Deep Learning with Lean 4

A formal verification of the math of modern deep learning, written as a Lean 4 blueprint project and shipped as the code it proves. Mathlib's fderiv is the foundation; every layer's backward is derived as a vector-Jacobian product rather than asserted -- dense, ReLU, softmax cross-entropy, 2D convolution, max-pool, Bat...

A Learnable Sparse Attention Graph Architecture for Heterogeneous Multi-UAV Air-to-Ground Mission Planning

In the complex problem of air-to-ground mission planning, multi-UAV systems face significant challenges such as system complexity and heterogeneity, insufficient target observability, and difficulties in collaborating information sharing. To address these issues, this paper proposes a novel learnable sparse attention g...

Verified Deep Learning with Lean 4

A formal verification of the math of modern deep learning, written as a Lean 4 blueprint project and shipped as the code it proves. Mathlib's fderiv is the foundation; every layer's backward is derived as a vector-Jacobian product rather than asserted -- dense, ReLU, softmax cross-entropy, 2D convolution, max-pool, Bat...

Physics-informed graph neural network‑based analysis method for elastic static responses of spatial latticed shells

Dynamic Event Knowledge Graph–Based Fault Diagnosis for Multisensor Electromechanical Systems of Aviation Equipment and Its Application

An event knowledge graph is leveraged for UAV sensor fault diagnosis: the graph’s architecture inherently structures the array of distinct sensors, and causal logic derived from event progression boosts the graph nodes’ ability to extract meaningful features, and a relationship-focused attention mechanism captures spat...

Blockchain based intelligent authentication and privacy-preserving information sharing in internet of vehicles networks for smart cities using temporal dynamic graph neural network