Unified thermodynamic cosmology developed by Morten Magnusson — connecting energy flow, entropy, and structure across scales.

🖊️ Implement a feedforward neural network from scratch to accurately classify handwritten digits using the MNIST dataset with pure NumPy.

🧬 Predict drug interactions with the open-source CYP3A4 system, essential for research, education, and enhancing patient safety in medication management.

Transform geospatial relations into graph representations designed for spatial network analysis and Graph Neural Networks (GNNs).

A hpc LLVM Pass extracting semantic Control-Data Flow Graphs (CDFG) from Intermediate Representation for Graph Neural Networks. Enables cross-language code retrieval and clone detection beyond token-based approaches.

Modern Grid Management System

[NeurIPS 2025] Association-Focused Path Aggregation for Graph Fraud Detection

Transforming relational data into graph structures to improve GNN performance using PyTorch Geometric.

A Resource-Constrained Project Scheduling Agent (RCPSA) based on GNN, e-greedy DQN, and model-based planning

GraphSAGE + XGBoost ensemble for DNS malware detection. Achieved 97.43% accuracy on 200K-domain Zenodo dataset. Internship project.

A graph neural network for the segmentation and object detection in radar point clouds.

The integration of HugeGraph with AI/LLM & GraphRAG

A robust Neuro-Symbolic Sudoku Solver combining Graph Attention Networks (GATv2) with Dynamic Constraint Propagation. Efficiently solves NP-hard puzzles where traditional backtracking fails

Dashboard for 🩺PIE-Med, a cutting-edge system designed to enhance medical decision-making through the integration of Graph Neural Networks (GNNs) ⚙️, Explainable AI (XAI)❓ techniques, and Large Language Models (LLMs) 🧠.

Dashboard for 🩺PIE-Med, a cutting-edge system designed to enhance medical decision-making through the integration of Graph Neural Networks (GNNs) ⚙️, Explainable AI (XAI)❓ techniques, and Large Language Models (LLMs) 🧠.

TCN + Bi-Mamba/FLA + GNN + Dynamic LPE for Clinical EEG Seizure Detection

LangGraph BioFlow is an AI-orchestrated bioinformatics workflow framework combining LangGraph, Nextflow, RAG, and GNN modules to manage adaptive pipelines, perform real-time QC, pathway enrichment, gene-pathway visualization, and predict drug-target interactions intelligently.

Graph-based Agricultural Reasoning for Diagnosis via Multi-Modal Fusion.

A production-grade optimization workflow for Graph Neural Networks (GNNs) in drug discovery

This code is related to “n‑HDP‑GNN: community‑aware Bayesian clustering for over‑smoothing‑resilient, communication‑efficient distributed GNNs” research paper