
-
NetBase Quid
- Taipei, Taiwan
- https://www.linkedin.com/in/huang-yu-hsiang-19911120/
Starred repositories
Reference models and tools for Cloud TPUs.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.
A full Python Implementation of the ROUGE Metric (not a wrapper)
Vector Quantized VAEs - PyTorch Implementation
Efficient layer normalization GPU kernel for Tensorflow
Solutions to LeetCode problems; updated daily. Subscribe to my YouTube channel for more.
PyTorch implementations of Generative Adversarial Networks.
Junction Tree Variational Autoencoder for Molecular Graph Generation (ICML 2018)
Tensorflow implementation of Hyperspherical Variational Auto-Encoders
Neural relational inference for interacting systems - pytorch
Generating Natural Adversarial Examples, ICLR 2018
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun
InferSent sentence embeddings
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Theano reimplementation of pixelCNN architecture
A recurrent neural network designed to generate classical music.
Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"
Code to accompany the paper "Learning Graphical State Transitions"
Sparse and structured neural attention mechanisms
Various tutorials given for welcoming new students at MILA.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.