This repo combines Proximal Policy Optimization (PPO) with a geometric linear velocity control for path-following and collision avoidance in 3D environments. A Variational Autoencoder (VAE) compresses high-dimensional depth image inputs from the drone's depth camera, the sole exteroceptive sensor. Digital Twins (DT) test the sim2real readiness.

Variational Autoencoder (VAE) in PyTorch

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

Generation and evaluation of synthetic time series datasets (also, augmentations, visualizations, a collection of popular datasets)

Counterfactual inference for 3D brain imaging using deep structural causal models.

List of molecules (small molecules, RNA, peptide, protein, enzymes, antibody, and PPIs) conformations and molecular dynamics (force fields) using generative artificial intelligence and deep learning

Implementation of a Variational Autoencoder (VAE) for meandering river images using PyTorch

PyTorch implementation of Forget-me-not

List of Molecular and Material design using Generative AI and Deep Learning

Generating gray scale images of numerical digit by using variational autoencoder

Generative Adversarial Networks in Pytorch and Tensorflow

Generate synthetic medical data from a patient population dataset.

Convolutional version of the beta-Intact-VAE to help control for spurious correlations in counterfactual image generation.

Pytorch版本实现的VAE和公式推导

Variational Auto Encoder and Conditional Variational Auto Encoder Implementation

Vector Quantized Variational Auto-Encoder (VQ-VAE): Neural Discrete Representation Learning

Official code for "DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation" (TPAMI2022) and "Are We Evaluating Rigorously? Benchmarking Recommendation for Reproducible Evaluation and Fair Comparison" (RecSys2020)

Autoencoder models using PyTorch

Authors' PyTorch implementation of lossy image compression methods based on hierarchical VAEs

Using Non-negative Matrix Factorization (NMF) and Variational Autoencoder (VAE) machine learning architectures to analyze spatial and spectral features of hyperspectral cathodoluminescence (CL) spectroscopy images taken from hybrid inorganic-organic perovskite material