Michael A. Riegler

moltbook-observatory. Data collection from Moltbook for research

biomedia-2019. ACM-Grand-Challenge-2019-Biomedia

simpleaudit. Allows to red-team your AI systems through adversarial probing. It is simple, effective, and requires minimal setup.

PGR-103-2020. This is the code example repository for PGR-103-2020. The published code is for educational purposes only. Reusing the code for other purposes than this needs to be approved by individual code authors.

openai-healthbench-analysis. his repository contains code and resources related to an in-depth analysis of OpenAI's HealthBench, a benchmark designed for evaluating Large Language Models in the healthcare sector.

normedqa. NorMedQA is designed to evaluate the medical knowledge and reasoning capabilities of large language models (LLMs) in Norwegian context (Bokmål and Nynorsk). The benchmark consists of 1313 question-and-answer pairs covering various medical fields.

medgemma-visual-chat. Visual chat example using the medgemma model from Google

ai-secbench. Security-focused AI reasoning benchmark for evaluating cipher analysis, steganography detection, and adversarial robustness

local-agentic-rag-gemma3. A local agent RAG implementation using Gemma3 via Ollama

medgemma-exploration. Simple how to and exploration of MedGemma from Google and comparison with Gemma3 using the Kvasir dataset

imagefeatures. Simple package to use old school image features, and avoid them being forgotten.

tm-swarm. A Python framework for N-agent collective learning using Tsetlin Machines and synthetic data sharing, supporting zero-shot sensor onboarding and LLM-driven feature extraction.

images-direct-load-keras. This repo provides code that shows how images can be directly loaded for being useable in Keras (or others) without using the generator function. This can be useful for some applications.

AMSS-workshop.

meta-web-ssl-examples. This repository showcases various ways to utilize and visualize features from Meta AI's new Web-ssl model series facebook/webssl-dino300m-full2b-224, Vision Transformers trained using self-supervised learning without language data. Examples range from basic feature extraction and visualization on single images to videos.

Medico-2021-Team-Medical-XAI. Repository for the submission of team medical XAI for mediaeval medico 2021.

gemma4-video-chat. Browser-based video chat with Gemma 4 running locally via llama.cpp