Pinned Repositories
dart_detection
A repository to automatically detect the location of darts on a board with aruco markers.
ipft_pomdp_solver
This repository contains code I have written for my Master's thesis. It is a C++ implementation of the IPFT POMDP solver.
iwa
A new method for ensemble learning in unsupervised domain adaptation with asymptotically optimal error rate.
metaworld
An open source robotics benchmark for meta- and multi-task reinforcement learning
ml-starter
A template for quickly implementing ML ideas 🧠⚡
polyvision
A C++ library wrapped in Python for visible area calculations with 2D polygons using CGAL.
RNN-adaptation-fewshot
Fork for dynamical systems experiments of the paper "Few-Shot Learning by Dimensionality Reduction in Gradient Space"
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
staz
Collection of code snippets for statistical analysis of experiment results.
Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
maximilianmbeck's Repositories
maximilianmbeck/dart_detection
A repository to automatically detect the location of darts on a board with aruco markers.
maximilianmbeck/ipft_pomdp_solver
This repository contains code I have written for my Master's thesis. It is a C++ implementation of the IPFT POMDP solver.
maximilianmbeck/iwa
A new method for ensemble learning in unsupervised domain adaptation with asymptotically optimal error rate.
maximilianmbeck/metaworld
An open source robotics benchmark for meta- and multi-task reinforcement learning
maximilianmbeck/ml-starter
A template for quickly implementing ML ideas 🧠⚡
maximilianmbeck/polyvision
A C++ library wrapped in Python for visible area calculations with 2D polygons using CGAL.
maximilianmbeck/RNN-adaptation-fewshot
Fork for dynamical systems experiments of the paper "Few-Shot Learning by Dimensionality Reduction in Gradient Space"
maximilianmbeck/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
maximilianmbeck/staz
Collection of code snippets for statistical analysis of experiment results.
maximilianmbeck/Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
maximilianmbeck/viz
Collection of code snippets for any kinds of visualizations related to machine learning.