Marcel Neunhoeffer's repositories
arf_paper
Code and materials to reproduce adversarial RF paper
be_great
A novel approach for synthesizing tabular data using pretrained large language models
dataverse-r-study
Data and code for a large-scale study on research code quality and execution at Harvard Dataverse.
dp-data
A repository for preprocessing datasets to use for private synthetic data generation. Some preprocessed datasets have also been included.
ds-wgan
Design of Simulations using WGAN
dswgan-paper
Replication files for "Using WGANs for the Design of Monte Carlo Simulations"
llama
Inference code for LLaMA models
minbpe
Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
ml-stable-diffusion
Stable Diffusion with Core ML on Apple Silicon
mlx-examples
Examples in the MLX framework
private-pgm
An implementation of the tools described in the paper entitled "Graphical-model based estimation and inference for differential privacy"
PrivaTree
PrivaTree: An algorithm for training differentially-private decision trees
twinify
A software package for privacy-preserving generation of a synthetic twin to a given sensitive data set.