Skip to content
View MaxWolf-01's full-sized avatar
:electron:
:electron:
28 followers · 76 following

Achievements

Achievement: Pair Extraordinairex2Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex2Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Highlights

  • Pro

Block or report MaxWolf-01

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MaxWolf-01/README.md

Hey, I'm Max, AI student at JKU Linz working on biologically-inspired neural architectures.

I'm interested in how intelligence emerges from simple components - cells self-organizing into adaptive networks that learn, communicate, and remember. Drawing ideas from artificial life, neuroevolution, and developmental biology, I try to find the minimal ingredients for continual learning and open-ended discovery.

Currently exploring:

  • Self-organizing neural architectures with learned dynamic connectivity
  • Meta-learning where shared parameters define how neurons communicate while their context determines their role
  • Automated curricula optimizing task diversity and learning potential via LLM-guided exploration

On my website mwolf.dev, you'll find detailed notes and thoughts (major updates coming soon).

Below are highlighted projects and paper implementations.

Paper Replicas
Project Paper Status
es-torch Evolution Strategies as a Scalable Alternative to Reinforcement Learning ✅
multi-agent-transformer Multi-Agent Reinforcement Learning is a Sequence Modeling Problem 🚧
LNDP Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning 🚧
Misc
Project Description Tools/Languages
dotfiles Config files, utility scripts, ... Neovim Zsh Lua
Obsidian Homepage Personal-stats visualization from Obsidian daily-note metadata JavaScript Chart.js Obsidian
aleator RNG-based habit formation app. Website React TypeScript FastAPI Claude
High School Projects
Project Description Tools/Languages
Sentinel-2 Landcover Classification (Diploma Project) Landcover classification on sentinel-2 data with Prithvi, EfficientNet-Unet and OSM / CNES Landcover labels. Python Lightning GeoJSON
TruthTabler Boolean expression parser, simplifier, converter. Python
2048JavaFx-Bot 2048-Game in JavaFx, including a parallel expectimax bot which gets to 4096 most of the time. Java
Metrics

Pinned Loading

  1. dotfiles dotfiles Public

    My dotfiles for linux

    Shell 5

  2. neuro-soup/es-torch neuro-soup/es-torch Public

    Evolution Strategies (OpenAI) in pytorch + distributed

    Python 5

  3. aleator aleator Public

    RNG that helps you make decisions and track progress

    TypeScript 1

  4. sentinel2-landcover-classification sentinel2-landcover-classification Public

    Landcover classification on sentinel-2 data with Prithvi, EfficientNet-Unet and OSM / CNES Landcover labels.

    Python 10

  5. TruthTabler TruthTabler Public

    Solves boolean expressions and simplifies them, draws logic-circuits and constructs circuits and boolean terms from truth-table values and converts boolean expressions to NAND and NOR.

    Python 7 1

  6. 2048JavaFx-Bot 2048JavaFx-Bot Public

    2048-Game in JavaFx, including a bot which gets to 4096 most of the time.

    Java 5