Skip to content
View Flashness123's full-sized avatar

Highlights

  • Pro

Block or report Flashness123

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
Flashness123/README.md

Hi, I'm Lukas

I like figuring out how things actually work. Not the surface version, but the part underneath where you can see why an algorithm behaves the way it does. The fastest way I've found to get there is to build the thing myself, so a lot of what I make are from-scratch implementations of ideas I wanted to genuinely understand rather than just import.

I'm drawn to machine learning and reinforcement learning. I'm especially interested in how agents learn from trial and error, and in evolutionary methods, which I find genuinely fascinating in their own right.

When I run into something I don't know, I've learned to treat that as the interesting part rather than a wall. I'd rather be a little out of my depth and come out knowing the thing than stay where it's comfortable.

A few things I've built

  • SimpleSimpleNEAT — NEAT written from scratch: neural networks that evolve their own structure to solve control tasks. The project that got me hooked on evolutionary algorithms.
  • transformer-gnn-layer — a graph-convolution layer dropped into a LLaMA decoder stack, to see what happens when you mix a transformer with a graph neural network.
  • DocSeg2 and my bachelor thesis — document AI: pulling structure out of messy scanned pages and technical drawings with detection models and fine-tuned vision-language models.
  • sNeuron-TST — worked inside a research codebase for a text-style-transfer paper and upstreamed fixes so it runs on current libraries.
  • finaler-Beleg-2022 and a small x86 operating system — C++ from the ground up, down to a hand-written linked list and a kernel with its own keyboard and screen drivers.
  • Race_history and Pic Roulette — full apps I built end to end, the second a multiplayer game that's live on the Play Store.

Pinned Loading

  1. Bachelorarbeit Bachelorarbeit Public

    Bachelor thesis: automated classification & metadata extraction of German technical drawings by fine-tuning Donut and LayoutLMv3

    Jupyter Notebook

  2. DocSeg2 DocSeg2 Public

    Document layout analysis pipeline (bachelor thesis): Deformable DETR + Table Transformer + OCR to segment scanned pages into text, tables and figures

    Python

  3. Race_history Race_history Public

    Web app for tracking downhill/longboard races and spots worldwide — FastAPI + Postgres backend, Next.js frontend. Paused project.

    TypeScript

  4. SimpleSimpleNEAT SimpleSimpleNEAT Public

    From-scratch NEAT (NeuroEvolution of Augmenting Topologies) evolving neural networks to solve Gymnasium control tasks

    Python

  5. transformer-gnn-layer transformer-gnn-layer Public

    A GCN layer injected into a LLaMA decoder stack — hybrid Transformer + graph neural network, with a Cora node-classification demo.

    Python

  6. wenlai-lavine/sNeuron-TST wenlai-lavine/sNeuron-TST Public

    EMNLP 2024 | Style-Specific Neurons for Steering LLMs in Text Style Transfer

    Python 14 2