Shi-Yuan Ma's starred repositories
neural-network-for-nonlocality-in-networks
Code for the work in: https://www.nature.com/articles/s41534-020-00305-x Basically a generative neural network to tackle the classical causal inference problem encountered in quantum network nonlocality.
Single-Photon-Detection-Neural-Networks
Physics-aware stochastic training for single-photon-detection neural networks (SPDNNs)
improved_wgan_training
Code for reproducing experiments in "Improved Training of Wasserstein GANs"
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.
Wasserstein-Generative-Adversarial-Network
In this Machine Learning Exam I created two types of Generative Adversarial Networks (GANs) with different loss functions. The aim of the two networks is to train the generator network to generate samples from a given probability distribution in a way that the discriminator cannot distinguish it from real samples. In this example I worked with data from a 2D Ising Model which is one of the most successful and broadly applicable models in statistical physics.
QuDDPM_reproduce_and_extend
Code to reproduce paper regarding quantum diffusion model and extend: Zhang, Bingzhi, et al. "Generative quantum machine learning via denoising diffusion probabilistic models." arXiv preprint arXiv:2310.05866 (2023).
stable-diffusion
A latent text-to-image diffusion model
Correlated-VAEs
Code for my ICML 2019 paper "Correlated Variational Auto-Encoders"
set_transformer
Pytorch implementation of set transformer
GaussianSSF.jl
Quantum split-step Fourier simulations for nonlinear Gaussian-state pulse propagation
Quantum-Gaussian-Information-Toolbox
QuGIT is a numerical toolbox in Python for simulation of gaussian quantum states and their time evolution through unconditional and conditional dynamics
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
DenseNet
This repository contains a PyTorch implementation of the paper Densely Connected Convolutional Networks trained on the MNIST dataset. The code is based on this excellent PyTorch example for training DenseNet.(https://github.com/pytorch/vision/blob/master/torchvision/models/densenet.py)
MLP-Mixer-CIFAR10
Implements MLP-Mixer (https://arxiv.org/abs/2105.01601) with the CIFAR-10 dataset.
adversarial-autoencoder
Chainer implementation of adversarial autoencoder (AAE)
binary-stochastic-neurons
Binary Stochastic Neurons in PyTorch
Adversial_AutoEncoder
Adversial AutoEncoder in PyTorch
Pytorch-autoencoder-mlp
MLP for MNIST Classification(Autoencoder_Pretrain)