-
RWTH Aachen
- Aachen
Stars
Qualitative and Quantitative Verification Tool for Learning-enabled Cyber-Physical Systems
The library for symbolic interval
GUI for a Vocal Remover that uses Deep Neural Networks.
TorchVNNLIB is a tool to convert .vnnlib file into .pth file with tourch tensors.
GDVB| Systematic Generation of Diverse Benchmarks for DNN Verification
Code for the automation of the VNN-COMP, used in 2022-2024
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
A tool for construction and conversion of neural networks across different standards
A package for parsing neural network properties in VNN-LIB format
The ArtificialSongGenerator automatically composes and compiles the Artifical Audio Multitrack dataset (AAM).
AAAI'25 Tutorial on "(Really) Using Counterfactuals to Explain AI Systems": https://sites.google.com/view/cfe-tutorial-aaai-25/startseite
A lightweight Python package for setting up robustness experiments and to compute robustness distributions.
Codebase for our work titled 'Robustness to Perturbations in the Frequency Domain: Neural Network Verification and Certified Training', 2025 IEEE/CVF Winter Conference on Applications of Computer V…
Accelerated multiplications with kernel matrices
CTRAIN is a unified, modular and comprehensive package for certifiably training neural networks and evaluating their robustness.
ASF is a flexible Python library for algorithm selection
[NeurIPS 2024 Datasets and Benchmarks Track] Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
Feature engineering and selection open-source Python library compatible with sklearn.
Automatic extraction of relevant features from time series:
Model interpretability and understanding for PyTorch
Training Sparse Autoencoders on Language Models
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.