Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning

Solving High Dimensional Partial Differential Equations with Deep Neural Networks

An open-ended, self-improving AI system that evolves its own source code using a local LLM. Built for autonomy, reflection, and code evolution, running locally via Ollama

This repository collects lecture slides, assignments (CAs), code notebooks, reports, and reference papers used in the "Deep Generative Models" course (University of Tehran). The materials are organized to be reproducible and educational: each assignment contains an annotated Jupyter notebook, supporting code, and a report.Deep Generative Models

Official Tensorflow implementation for Deep Generative Positive-Unlabeled Learning under Selection Bias (VAE-PU) in CIKM 2020.

A Dusty Gas model in order to simulate the mass transfer and the voltage loss in a Solid Oxide Fuel Cell.

# EvoDistill 🧬 **Lossless (and beyond) LLM distillation powered by the Darwin Gödel Machine** From mere approximation → **100%+ teacher retention** at 5-10× smaller size and speed. Inspired by the Darwin Gödel Machine (arXiv:2505.22954) and classic knowledge distillation. EvoDistill evolves the entire distillation pipeline — hyperparameters,

GRASS GIS toolset for the import of digital elevation models (DEMs; German: DOMs). It includes import addons for the open geodata elevation models for Germany.

Konvertiert GeoTiff-Dateien in Koordinatenlisten

Deep Generative Models

Clip Digital Elevation Models (DEMs) using a shapefile or GeoJSON polygon, Python only.

Calculates DGMs/DSMs from LAZ files