TotalVibeSegmentator: Full Torso Segmentation for the NAKO and UK Biobank in Volumetric Interpolated Breath-hold Examination Body Images

NanoGPT (124M) in 5 minutes

A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.

KFAdam: A Kalman filter based optimizer for de-noising SGD

Fast, memory-efficient, scalable optimization of deep learning with differential privacy

Privacy backdoors

Equivariant ConvNets for Differentially Private Image Classification.

RadImageNet, a pre-trained convolutional neural networks trained solely from medical imaging to be used as the basis of transfer learning for medical imaging applications.

A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model

PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.

PriMIA: Privacy-preserving Medical Image Analysis

High-Resolution Image Synthesis with Latent Diffusion Models

Code for "Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis" @ PAKDD 2023

Repository to train Latent Diffusion Models on Chest X-ray data (MIMIC-CXR) using MONAI Generative Models

Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)

Anomaly detection with diffusion models

AI Toolkit for Healthcare Imaging

Private Evolution: Generating DP Synthetic Data without Training [ICLR 2024, ICML 2024]

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Breaching privacy in federated learning scenarios for vision and text

Supplementary code for the paper "Hyperbolic Image Embeddings".

Code for paper Fully Hyperbolic Neural Networks

Hyperbolic Graph Convolutional Networks in PyTorch.

Implementation of hyperbolic NNs and GNNs

[NeurIPS 2023] Riemannian Residual Neural Networks (https://arxiv.org/abs/2006.10254)

Differentially private graph neural networks (GNNs)