A personal companion for planning, habits and focus. Daily check-ins meet a clear view of everyday life.
FlutterDartPython
More about this project
A mobile-first coaching app built with Flutter, FastAPI and Supabase. Guest mode makes it possible to explore without an account; planning and guidance are based on explicit user input.
Personal weekly meal plans, matching shopping lists and upcoming meals at a glance. Also known as V&M Fuel.
JavaScriptMeal Planning
More about this project
A nutrition project built around personal preferences, weekly planning and shopping lists. The original V&M Fuel project website remains available in the archive.
WORKSPACE◈ Portfolio◇ Playground+ New projectCodex · Claude · Grok
✦ Codex
Build a useful app.
✓Understand the project
✓Implement changes
◌Review the result
An idea becomes an app.↑
Demo with sample content
03 / Web
Codex UI
A dedicated interface for agentic development: projects, chats and multiple coding agents in one place.
TypeScriptWeb UI
More about this project
A personal web app for orchestrating coding agents, managing projects and chats, and voice input. The visual preview is an illustrative demo with sample content.
Private source
YAPP AI / VOICE TO TEXT
Speak it. Keep it.
00:12
TRANSCRIPTION✦
Capture a new idea.
Give the thought room to grow.
Windows + AndroidDemo with sample content
04 / AI & Research
Yapp AI
Speak instead of typing: native voice input for Windows and Android, with separate meeting recording and transcription.
JavaC#Speech-to-Text
More about this project
A native application in development, featuring a microphone overlay, dictation history and configurable speech providers. Device validation is still part of ongoing development.
Private source
ZERO-SHOT / CHEST X-RAY
Image meets language.
Image
Text prompts
Shared embedding space
Multiple findings ↗
Research · model and prompt comparison
05 / AI & Research
Zero-Shot Chest X-Ray
Which findings can vision-language models identify without task-specific training? Comparing BioMedCLIP and MedCLIP with different prompting strategies on chest X-rays.
PythonVision-Language ModelsZero-Shot Learning
More about this project
Project in focus
Challenge
Explore how vision-language models identify multiple findings in chest X-rays without task-specific training.
Research project
We compared BioMedCLIP and MedCLIP and different prompting strategies across multiple datasets.
Technical approach
Positive and negative prompts, LLM-generated descriptions and composed strategies are evaluated through image-text similarity.
Finding
The benefit of a prompting strategy strongly depends on the model and dataset. This is a research comparison, not a clinical product.
Private source
3D VISION / GAUSSIAN SPLATTING
Many views. One scene.
Concept illustrationCameras → 3D Gaussians → new views
06 / AI & Research
3D Reconstruction with Gaussian Splatting
A team project reconstructing 3D scenes from multiple calibrated camera images. A neural model produces a 3D Gaussian representation that can be rendered from new viewpoints.
PythonPyTorch3D Gaussian Splatting
More about this project
Project in focus
Challenge
Reconstruct a 3D scene from multiple calibrated camera images and render new viewpoints.
Team project
We developed a pipeline that combines features from multiple cameras to predict a 3D representation.
Technical approach
A neural model produces a representation using 3D Gaussian Splatting. Model training and rendering are part of the same pipeline.
Outcome
Reconstructed scenes can be rendered from new viewpoints. Reconstruction quality was evaluated in the project.
Private source
TÜBINGEN / SEARCH ENGINE
Your city. Searchable.
Original project interface
07 / AI & Research
Tübingen Search Engine
A search engine for websites about Tübingen: crawling, indexing and ranking in a collaborative university project.
PythonStreamlitInformation Retrieval
More about this project
Created in the Modern Search Engines course. A pipeline turns websites into a searchable index and presents results through a Streamlit interface.
SAC ↔ Agent vs. agentTraining → Benchmark → Competition
08 / AI & Research
Hockey RL Agents
Developing and training reinforcement learning agents to face other agents in a provided hockey environment. The project concluded with a competition between teams.
PythonReinforcement LearningSoft Actor-Critic
More about this project
Project in focus
Challenge
Train an agent for an existing hockey environment to compete against other teams.
My contribution to the team
Soft Actor-Critic, training against a pool of opponents and benchmarks to compare models.
Technical approach
The agent learns its strategy through reinforcement learning; different training opponents allow comparisons under different conditions.
Outcome
The trained agent participated in the final competition against agents from other teams.
Private source
It starts with a sketch.
Sketch + Prompt → Image
09 / AI & Research
Pencil2Pixel
From a first sketch to an AI-generated image. A drawing canvas meets prompts, visual styles and creative experiments.
PythonJavaScriptGenerative AI
More about this project
Draw in the browser, add a prompt and generate images through a Python backend. The project includes brushes, an eraser, undo/redo and adjustable generation parameters.
It starts with a sketch.
